diff --git a/.DS_Store b/.DS_Store
new file mode 100644
index 0000000000000000000000000000000000000000..e3ed38467b9443a1ed268e71ce82815be7c1adee
Binary files /dev/null and b/.DS_Store differ
diff --git a/.gitattributes b/.gitattributes
index 28b0217abf662dafdb4409aa71e39e969b3c3463..70898625f0e2789ba55c622119da6ebc985092e6 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -123,3 +123,77 @@ DeepSeek-R1-Distill-Qwen-32B_float16/model-00013-of-00013.safetensors filter=lfs
DeepSeek-R1-Distill-Qwen-32B_float16/model-00001-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-32B_float16/model-00012-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-32B_float16/model-00004-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-4bit/model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-4bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-6bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-4bit/model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-6bit/model-00006-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-4bit/model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-4bit/model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-6bit/model-00002-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-6bit/model-00003-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-6bit/model-00005-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-6bit/model-00004-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-6bit/model-00001-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-3bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-3bit/model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-3bit/model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-3bit/model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-float16/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-float16/model-00010-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-float16/model-00007-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-float16/model-00002-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-float16/model-00008-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-float16/model-00011-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-float16/model-00009-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-float16/model-00006-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-float16/model-00003-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-float16/model-00005-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-float16/model-00012-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-float16/model-00001-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-float16/model-00013-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-float16/model-00004-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00010-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00007-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-bfloat16/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00002-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00008-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00009-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00011-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00006-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00003-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00005-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00013-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-8bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00012-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00001-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00004-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-8bit/model-00005-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-8bit/model-00007-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-8bit/model-00001-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-8bit/model-00004-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-8bit/model-00002-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-8bit/model-00006-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-8bit/model-00003-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
diff --git a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/config.json b/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..b0b83d44724403ed68786d8f2330d57dd6970756
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/config.json
@@ -0,0 +1,4021 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 5120,
+ "initializer_range": 0.02,
+ "intermediate_size": 27648,
+ "max_position_embeddings": 131072,
+ "max_window_layers": 64,
+ "model_type": "qwen2",
+ "num_attention_heads": 40,
+ "num_hidden_layers": 64,
+ "num_key_value_heads": 8,
+ "quantization": {
+ "group_size": 64,
+ "bits": null,
+ "model.embed_tokens": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.0.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.0.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.0.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.0.self_attn.rope": false,
+ "model.layers.0.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.0.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.0.input_layernorm": false,
+ "model.layers.0.post_attention_layernorm": false,
+ "model.layers.1.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.1.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.1.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.1.self_attn.rope": false,
+ "model.layers.1.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.1.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.1.input_layernorm": false,
+ "model.layers.1.post_attention_layernorm": false,
+ "model.layers.2.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.2.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.2.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.2.self_attn.rope": false,
+ "model.layers.2.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.2.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.2.input_layernorm": false,
+ "model.layers.2.post_attention_layernorm": false,
+ "model.layers.3.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.3.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.3.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.3.self_attn.rope": false,
+ "model.layers.3.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.3.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.3.input_layernorm": false,
+ "model.layers.3.post_attention_layernorm": false,
+ "model.layers.4.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.4.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.4.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.4.self_attn.rope": false,
+ "model.layers.4.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.4.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.4.input_layernorm": false,
+ "model.layers.4.post_attention_layernorm": false,
+ "model.layers.5.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.5.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.5.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.5.self_attn.rope": false,
+ "model.layers.5.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.5.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.5.input_layernorm": false,
+ "model.layers.5.post_attention_layernorm": false,
+ "model.layers.6.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.6.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.6.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.6.self_attn.rope": false,
+ "model.layers.6.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.6.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.6.input_layernorm": false,
+ "model.layers.6.post_attention_layernorm": false,
+ "model.layers.7.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.7.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.7.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.7.self_attn.rope": false,
+ "model.layers.7.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.7.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.7.input_layernorm": false,
+ "model.layers.7.post_attention_layernorm": false,
+ "model.layers.8.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.8.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.8.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.8.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.8.self_attn.rope": false,
+ "model.layers.8.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.8.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.8.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.8.input_layernorm": false,
+ "model.layers.8.post_attention_layernorm": false,
+ "model.layers.9.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.9.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.9.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.9.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.9.self_attn.rope": false,
+ "model.layers.9.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.9.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.9.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.9.input_layernorm": false,
+ "model.layers.9.post_attention_layernorm": false,
+ "model.layers.10.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.10.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.10.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.10.self_attn.rope": false,
+ "model.layers.10.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.10.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.10.input_layernorm": false,
+ "model.layers.10.post_attention_layernorm": false,
+ "model.layers.11.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.11.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.11.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.11.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.11.self_attn.rope": false,
+ "model.layers.11.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.11.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.11.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.11.input_layernorm": false,
+ "model.layers.11.post_attention_layernorm": false,
+ "model.layers.12.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.12.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.12.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.12.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.12.self_attn.rope": false,
+ "model.layers.12.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.12.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.12.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.12.input_layernorm": false,
+ "model.layers.12.post_attention_layernorm": false,
+ "model.layers.13.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.13.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.13.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.13.self_attn.rope": false,
+ "model.layers.13.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.13.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.13.input_layernorm": false,
+ "model.layers.13.post_attention_layernorm": false,
+ "model.layers.14.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.14.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.14.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.14.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.14.self_attn.rope": false,
+ "model.layers.14.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.14.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.14.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.14.input_layernorm": false,
+ "model.layers.14.post_attention_layernorm": false,
+ "model.layers.15.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.15.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.15.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.15.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.15.self_attn.rope": false,
+ "model.layers.15.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.15.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.15.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.15.input_layernorm": false,
+ "model.layers.15.post_attention_layernorm": false,
+ "model.layers.16.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.16.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.16.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.16.self_attn.rope": false,
+ "model.layers.16.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.16.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.16.input_layernorm": false,
+ "model.layers.16.post_attention_layernorm": false,
+ "model.layers.17.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.17.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.17.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.17.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.17.self_attn.rope": false,
+ "model.layers.17.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.17.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.17.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.17.input_layernorm": false,
+ "model.layers.17.post_attention_layernorm": false,
+ "model.layers.18.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.18.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.18.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.18.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.18.self_attn.rope": false,
+ "model.layers.18.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.18.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.18.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.18.input_layernorm": false,
+ "model.layers.18.post_attention_layernorm": false,
+ "model.layers.19.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.19.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.19.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.19.self_attn.rope": false,
+ "model.layers.19.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.19.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.19.input_layernorm": false,
+ "model.layers.19.post_attention_layernorm": false,
+ "model.layers.20.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.20.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.20.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.20.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.20.self_attn.rope": false,
+ "model.layers.20.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.20.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.20.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.20.input_layernorm": false,
+ "model.layers.20.post_attention_layernorm": false,
+ "model.layers.21.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.21.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.21.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.21.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.21.self_attn.rope": false,
+ "model.layers.21.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.21.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.21.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.21.input_layernorm": false,
+ "model.layers.21.post_attention_layernorm": false,
+ "model.layers.22.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.22.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.22.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.22.self_attn.rope": false,
+ "model.layers.22.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.22.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.22.input_layernorm": false,
+ "model.layers.22.post_attention_layernorm": false,
+ "model.layers.23.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.23.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.23.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.23.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.23.self_attn.rope": false,
+ "model.layers.23.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.23.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.23.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.23.input_layernorm": false,
+ "model.layers.23.post_attention_layernorm": false,
+ "model.layers.24.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.24.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.24.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.24.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.24.self_attn.rope": false,
+ "model.layers.24.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.24.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.24.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.24.input_layernorm": false,
+ "model.layers.24.post_attention_layernorm": false,
+ "model.layers.25.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.25.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.25.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.25.self_attn.rope": false,
+ "model.layers.25.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.25.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.25.input_layernorm": false,
+ "model.layers.25.post_attention_layernorm": false,
+ "model.layers.26.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.26.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.26.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.26.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.26.self_attn.rope": false,
+ "model.layers.26.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.26.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.26.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.26.input_layernorm": false,
+ "model.layers.26.post_attention_layernorm": false,
+ "model.layers.27.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.27.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.27.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.27.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.27.self_attn.rope": false,
+ "model.layers.27.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.27.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.27.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.27.input_layernorm": false,
+ "model.layers.27.post_attention_layernorm": false,
+ "model.layers.28.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.28.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.28.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.28.self_attn.rope": false,
+ "model.layers.28.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.28.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.28.input_layernorm": false,
+ "model.layers.28.post_attention_layernorm": false,
+ "model.layers.29.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.29.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.29.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.29.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.29.self_attn.rope": false,
+ "model.layers.29.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.29.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.29.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.29.input_layernorm": false,
+ "model.layers.29.post_attention_layernorm": false,
+ "model.layers.30.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.30.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.30.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.30.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.30.self_attn.rope": false,
+ "model.layers.30.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.30.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.30.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.30.input_layernorm": false,
+ "model.layers.30.post_attention_layernorm": false,
+ "model.layers.31.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.31.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.31.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.31.self_attn.rope": false,
+ "model.layers.31.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.31.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.31.input_layernorm": false,
+ "model.layers.31.post_attention_layernorm": false,
+ "model.layers.32.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.32.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.32.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.32.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.32.self_attn.rope": false,
+ "model.layers.32.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.32.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.32.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.32.input_layernorm": false,
+ "model.layers.32.post_attention_layernorm": false,
+ "model.layers.33.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.33.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.33.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.33.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.33.self_attn.rope": false,
+ "model.layers.33.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.33.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.33.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.33.input_layernorm": false,
+ "model.layers.33.post_attention_layernorm": false,
+ "model.layers.34.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.34.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.34.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.34.self_attn.rope": false,
+ "model.layers.34.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.34.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.34.input_layernorm": false,
+ "model.layers.34.post_attention_layernorm": false,
+ "model.layers.35.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.35.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.35.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.35.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.35.self_attn.rope": false,
+ "model.layers.35.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.35.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.35.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.35.input_layernorm": false,
+ "model.layers.35.post_attention_layernorm": false,
+ "model.layers.36.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.36.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.36.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.36.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.36.self_attn.rope": false,
+ "model.layers.36.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.36.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.36.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.36.input_layernorm": false,
+ "model.layers.36.post_attention_layernorm": false,
+ "model.layers.37.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.37.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.37.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.37.self_attn.rope": false,
+ "model.layers.37.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.37.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.37.input_layernorm": false,
+ "model.layers.37.post_attention_layernorm": false,
+ "model.layers.38.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.38.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.38.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.38.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.38.self_attn.rope": false,
+ "model.layers.38.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.38.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.38.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.38.input_layernorm": false,
+ "model.layers.38.post_attention_layernorm": false,
+ "model.layers.39.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.39.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.39.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.39.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.39.self_attn.rope": false,
+ "model.layers.39.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.39.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.39.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.39.input_layernorm": false,
+ "model.layers.39.post_attention_layernorm": false,
+ "model.layers.40.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.40.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.40.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.40.self_attn.rope": false,
+ "model.layers.40.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.40.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.40.input_layernorm": false,
+ "model.layers.40.post_attention_layernorm": false,
+ "model.layers.41.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.41.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.41.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.41.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.41.self_attn.rope": false,
+ "model.layers.41.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.41.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.41.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.41.input_layernorm": false,
+ "model.layers.41.post_attention_layernorm": false,
+ "model.layers.42.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.42.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.42.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.42.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.42.self_attn.rope": false,
+ "model.layers.42.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.42.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.42.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.42.input_layernorm": false,
+ "model.layers.42.post_attention_layernorm": false,
+ "model.layers.43.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.43.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.43.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.43.self_attn.rope": false,
+ "model.layers.43.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.43.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.43.input_layernorm": false,
+ "model.layers.43.post_attention_layernorm": false,
+ "model.layers.44.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.44.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.44.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.44.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.44.self_attn.rope": false,
+ "model.layers.44.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.44.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.44.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.44.input_layernorm": false,
+ "model.layers.44.post_attention_layernorm": false,
+ "model.layers.45.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.45.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.45.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.45.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.45.self_attn.rope": false,
+ "model.layers.45.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.45.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.45.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.45.input_layernorm": false,
+ "model.layers.45.post_attention_layernorm": false,
+ "model.layers.46.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.46.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.46.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.46.self_attn.rope": false,
+ "model.layers.46.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.46.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.46.input_layernorm": false,
+ "model.layers.46.post_attention_layernorm": false,
+ "model.layers.47.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.47.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.47.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.47.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.47.self_attn.rope": false,
+ "model.layers.47.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.47.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.47.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.47.input_layernorm": false,
+ "model.layers.47.post_attention_layernorm": false,
+ "model.layers.48.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.48.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.48.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.48.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.48.self_attn.rope": false,
+ "model.layers.48.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.48.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.48.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.48.input_layernorm": false,
+ "model.layers.48.post_attention_layernorm": false,
+ "model.layers.49.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.49.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.49.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.49.self_attn.rope": false,
+ "model.layers.49.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.49.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.49.input_layernorm": false,
+ "model.layers.49.post_attention_layernorm": false,
+ "model.layers.50.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.50.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.50.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.50.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.50.self_attn.rope": false,
+ "model.layers.50.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.50.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.50.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.50.input_layernorm": false,
+ "model.layers.50.post_attention_layernorm": false,
+ "model.layers.51.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.51.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.51.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.51.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.51.self_attn.rope": false,
+ "model.layers.51.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.51.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.51.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.51.input_layernorm": false,
+ "model.layers.51.post_attention_layernorm": false,
+ "model.layers.52.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.52.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.52.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.52.self_attn.rope": false,
+ "model.layers.52.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.52.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.52.input_layernorm": false,
+ "model.layers.52.post_attention_layernorm": false,
+ "model.layers.53.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.53.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.53.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.53.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.53.self_attn.rope": false,
+ "model.layers.53.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.53.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.53.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.53.input_layernorm": false,
+ "model.layers.53.post_attention_layernorm": false,
+ "model.layers.54.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.54.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.54.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.54.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.54.self_attn.rope": false,
+ "model.layers.54.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.54.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.54.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.54.input_layernorm": false,
+ "model.layers.54.post_attention_layernorm": false,
+ "model.layers.55.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.55.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.55.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.55.self_attn.rope": false,
+ "model.layers.55.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.55.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.55.input_layernorm": false,
+ "model.layers.55.post_attention_layernorm": false,
+ "model.layers.56.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.56.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.56.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.56.self_attn.rope": false,
+ "model.layers.56.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.56.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.56.input_layernorm": false,
+ "model.layers.56.post_attention_layernorm": false,
+ "model.layers.57.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.57.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.57.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.57.self_attn.rope": false,
+ "model.layers.57.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.57.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.57.input_layernorm": false,
+ "model.layers.57.post_attention_layernorm": false,
+ "model.layers.58.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.58.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.58.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.58.self_attn.rope": false,
+ "model.layers.58.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.58.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.58.input_layernorm": false,
+ "model.layers.58.post_attention_layernorm": false,
+ "model.layers.59.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.59.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.59.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.59.self_attn.rope": false,
+ "model.layers.59.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.59.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.59.input_layernorm": false,
+ "model.layers.59.post_attention_layernorm": false,
+ "model.layers.60.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.60.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.60.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.60.self_attn.rope": false,
+ "model.layers.60.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.60.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.60.input_layernorm": false,
+ "model.layers.60.post_attention_layernorm": false,
+ "model.layers.61.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.61.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.61.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.61.self_attn.rope": false,
+ "model.layers.61.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.61.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.61.input_layernorm": false,
+ "model.layers.61.post_attention_layernorm": false,
+ "model.layers.62.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.62.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.62.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.62.self_attn.rope": false,
+ "model.layers.62.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.62.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.62.input_layernorm": false,
+ "model.layers.62.post_attention_layernorm": false,
+ "model.layers.63.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.63.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.63.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.63.self_attn.rope": false,
+ "model.layers.63.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.63.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.63.input_layernorm": false,
+ "model.layers.63.post_attention_layernorm": false,
+ "model.norm": false,
+ "lm_head": {
+ "group_size": 64,
+ "bits": 4
+ }
+ },
+ "quantization_config": {
+ "group_size": 64,
+ "bits": null,
+ "model.embed_tokens": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.0.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.0.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.0.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.0.self_attn.rope": false,
+ "model.layers.0.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.0.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.0.input_layernorm": false,
+ "model.layers.0.post_attention_layernorm": false,
+ "model.layers.1.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.1.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.1.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.1.self_attn.rope": false,
+ "model.layers.1.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.1.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.1.input_layernorm": false,
+ "model.layers.1.post_attention_layernorm": false,
+ "model.layers.2.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.2.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.2.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.2.self_attn.rope": false,
+ "model.layers.2.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.2.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.2.input_layernorm": false,
+ "model.layers.2.post_attention_layernorm": false,
+ "model.layers.3.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.3.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.3.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.3.self_attn.rope": false,
+ "model.layers.3.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.3.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.3.input_layernorm": false,
+ "model.layers.3.post_attention_layernorm": false,
+ "model.layers.4.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.4.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.4.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.4.self_attn.rope": false,
+ "model.layers.4.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.4.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.4.input_layernorm": false,
+ "model.layers.4.post_attention_layernorm": false,
+ "model.layers.5.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.5.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.5.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.5.self_attn.rope": false,
+ "model.layers.5.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.5.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.5.input_layernorm": false,
+ "model.layers.5.post_attention_layernorm": false,
+ "model.layers.6.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.6.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.6.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.6.self_attn.rope": false,
+ "model.layers.6.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.6.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.6.input_layernorm": false,
+ "model.layers.6.post_attention_layernorm": false,
+ "model.layers.7.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.7.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.7.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.7.self_attn.rope": false,
+ "model.layers.7.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.7.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.7.input_layernorm": false,
+ "model.layers.7.post_attention_layernorm": false,
+ "model.layers.8.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.8.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.8.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.8.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.8.self_attn.rope": false,
+ "model.layers.8.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.8.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.8.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.8.input_layernorm": false,
+ "model.layers.8.post_attention_layernorm": false,
+ "model.layers.9.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.9.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.9.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.9.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.9.self_attn.rope": false,
+ "model.layers.9.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.9.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.9.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.9.input_layernorm": false,
+ "model.layers.9.post_attention_layernorm": false,
+ "model.layers.10.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.10.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.10.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.10.self_attn.rope": false,
+ "model.layers.10.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.10.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.10.input_layernorm": false,
+ "model.layers.10.post_attention_layernorm": false,
+ "model.layers.11.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.11.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.11.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.11.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.11.self_attn.rope": false,
+ "model.layers.11.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.11.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.11.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.11.input_layernorm": false,
+ "model.layers.11.post_attention_layernorm": false,
+ "model.layers.12.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.12.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.12.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.12.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.12.self_attn.rope": false,
+ "model.layers.12.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.12.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.12.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.12.input_layernorm": false,
+ "model.layers.12.post_attention_layernorm": false,
+ "model.layers.13.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.13.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.13.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.13.self_attn.rope": false,
+ "model.layers.13.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.13.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.13.input_layernorm": false,
+ "model.layers.13.post_attention_layernorm": false,
+ "model.layers.14.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.14.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.14.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.14.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.14.self_attn.rope": false,
+ "model.layers.14.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.14.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.14.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.14.input_layernorm": false,
+ "model.layers.14.post_attention_layernorm": false,
+ "model.layers.15.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.15.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.15.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.15.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.15.self_attn.rope": false,
+ "model.layers.15.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.15.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.15.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.15.input_layernorm": false,
+ "model.layers.15.post_attention_layernorm": false,
+ "model.layers.16.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.16.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.16.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.16.self_attn.rope": false,
+ "model.layers.16.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.16.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.16.input_layernorm": false,
+ "model.layers.16.post_attention_layernorm": false,
+ "model.layers.17.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.17.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.17.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.17.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.17.self_attn.rope": false,
+ "model.layers.17.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.17.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.17.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.17.input_layernorm": false,
+ "model.layers.17.post_attention_layernorm": false,
+ "model.layers.18.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.18.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.18.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.18.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.18.self_attn.rope": false,
+ "model.layers.18.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.18.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.18.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.18.input_layernorm": false,
+ "model.layers.18.post_attention_layernorm": false,
+ "model.layers.19.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.19.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.19.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.19.self_attn.rope": false,
+ "model.layers.19.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.19.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.19.input_layernorm": false,
+ "model.layers.19.post_attention_layernorm": false,
+ "model.layers.20.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.20.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.20.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.20.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.20.self_attn.rope": false,
+ "model.layers.20.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.20.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.20.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.20.input_layernorm": false,
+ "model.layers.20.post_attention_layernorm": false,
+ "model.layers.21.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.21.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.21.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.21.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.21.self_attn.rope": false,
+ "model.layers.21.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.21.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.21.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.21.input_layernorm": false,
+ "model.layers.21.post_attention_layernorm": false,
+ "model.layers.22.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.22.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.22.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.22.self_attn.rope": false,
+ "model.layers.22.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.22.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.22.input_layernorm": false,
+ "model.layers.22.post_attention_layernorm": false,
+ "model.layers.23.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.23.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.23.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.23.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.23.self_attn.rope": false,
+ "model.layers.23.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.23.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.23.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.23.input_layernorm": false,
+ "model.layers.23.post_attention_layernorm": false,
+ "model.layers.24.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.24.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.24.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.24.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.24.self_attn.rope": false,
+ "model.layers.24.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.24.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.24.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.24.input_layernorm": false,
+ "model.layers.24.post_attention_layernorm": false,
+ "model.layers.25.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.25.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.25.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.25.self_attn.rope": false,
+ "model.layers.25.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.25.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.25.input_layernorm": false,
+ "model.layers.25.post_attention_layernorm": false,
+ "model.layers.26.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.26.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.26.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.26.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.26.self_attn.rope": false,
+ "model.layers.26.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.26.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.26.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.26.input_layernorm": false,
+ "model.layers.26.post_attention_layernorm": false,
+ "model.layers.27.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.27.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.27.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.27.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.27.self_attn.rope": false,
+ "model.layers.27.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.27.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.27.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.27.input_layernorm": false,
+ "model.layers.27.post_attention_layernorm": false,
+ "model.layers.28.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.28.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.28.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.28.self_attn.rope": false,
+ "model.layers.28.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.28.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.28.input_layernorm": false,
+ "model.layers.28.post_attention_layernorm": false,
+ "model.layers.29.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.29.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.29.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.29.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.29.self_attn.rope": false,
+ "model.layers.29.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.29.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.29.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.29.input_layernorm": false,
+ "model.layers.29.post_attention_layernorm": false,
+ "model.layers.30.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.30.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.30.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.30.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.30.self_attn.rope": false,
+ "model.layers.30.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.30.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.30.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.30.input_layernorm": false,
+ "model.layers.30.post_attention_layernorm": false,
+ "model.layers.31.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.31.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.31.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.31.self_attn.rope": false,
+ "model.layers.31.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.31.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.31.input_layernorm": false,
+ "model.layers.31.post_attention_layernorm": false,
+ "model.layers.32.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.32.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.32.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.32.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.32.self_attn.rope": false,
+ "model.layers.32.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.32.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.32.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.32.input_layernorm": false,
+ "model.layers.32.post_attention_layernorm": false,
+ "model.layers.33.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.33.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.33.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.33.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.33.self_attn.rope": false,
+ "model.layers.33.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.33.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.33.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.33.input_layernorm": false,
+ "model.layers.33.post_attention_layernorm": false,
+ "model.layers.34.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.34.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.34.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.34.self_attn.rope": false,
+ "model.layers.34.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.34.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.34.input_layernorm": false,
+ "model.layers.34.post_attention_layernorm": false,
+ "model.layers.35.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.35.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.35.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.35.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.35.self_attn.rope": false,
+ "model.layers.35.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.35.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.35.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.35.input_layernorm": false,
+ "model.layers.35.post_attention_layernorm": false,
+ "model.layers.36.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.36.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.36.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.36.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.36.self_attn.rope": false,
+ "model.layers.36.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.36.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.36.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.36.input_layernorm": false,
+ "model.layers.36.post_attention_layernorm": false,
+ "model.layers.37.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.37.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.37.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.37.self_attn.rope": false,
+ "model.layers.37.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.37.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.37.input_layernorm": false,
+ "model.layers.37.post_attention_layernorm": false,
+ "model.layers.38.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.38.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.38.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.38.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.38.self_attn.rope": false,
+ "model.layers.38.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.38.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.38.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.38.input_layernorm": false,
+ "model.layers.38.post_attention_layernorm": false,
+ "model.layers.39.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.39.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.39.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.39.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.39.self_attn.rope": false,
+ "model.layers.39.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.39.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.39.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.39.input_layernorm": false,
+ "model.layers.39.post_attention_layernorm": false,
+ "model.layers.40.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.40.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.40.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.40.self_attn.rope": false,
+ "model.layers.40.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.40.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.40.input_layernorm": false,
+ "model.layers.40.post_attention_layernorm": false,
+ "model.layers.41.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.41.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.41.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.41.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.41.self_attn.rope": false,
+ "model.layers.41.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.41.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.41.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.41.input_layernorm": false,
+ "model.layers.41.post_attention_layernorm": false,
+ "model.layers.42.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.42.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.42.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.42.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.42.self_attn.rope": false,
+ "model.layers.42.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.42.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.42.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.42.input_layernorm": false,
+ "model.layers.42.post_attention_layernorm": false,
+ "model.layers.43.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.43.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.43.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.43.self_attn.rope": false,
+ "model.layers.43.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.43.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.43.input_layernorm": false,
+ "model.layers.43.post_attention_layernorm": false,
+ "model.layers.44.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.44.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.44.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.44.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.44.self_attn.rope": false,
+ "model.layers.44.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.44.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.44.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.44.input_layernorm": false,
+ "model.layers.44.post_attention_layernorm": false,
+ "model.layers.45.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.45.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.45.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.45.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.45.self_attn.rope": false,
+ "model.layers.45.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.45.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.45.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.45.input_layernorm": false,
+ "model.layers.45.post_attention_layernorm": false,
+ "model.layers.46.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.46.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.46.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.46.self_attn.rope": false,
+ "model.layers.46.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.46.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.46.input_layernorm": false,
+ "model.layers.46.post_attention_layernorm": false,
+ "model.layers.47.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.47.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.47.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.47.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.47.self_attn.rope": false,
+ "model.layers.47.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.47.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.47.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.47.input_layernorm": false,
+ "model.layers.47.post_attention_layernorm": false,
+ "model.layers.48.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.48.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.48.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.48.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.48.self_attn.rope": false,
+ "model.layers.48.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.48.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.48.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.48.input_layernorm": false,
+ "model.layers.48.post_attention_layernorm": false,
+ "model.layers.49.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.49.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.49.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.49.self_attn.rope": false,
+ "model.layers.49.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.49.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.49.input_layernorm": false,
+ "model.layers.49.post_attention_layernorm": false,
+ "model.layers.50.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.50.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.50.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.50.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.50.self_attn.rope": false,
+ "model.layers.50.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.50.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.50.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.50.input_layernorm": false,
+ "model.layers.50.post_attention_layernorm": false,
+ "model.layers.51.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.51.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.51.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.51.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.51.self_attn.rope": false,
+ "model.layers.51.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.51.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.51.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.51.input_layernorm": false,
+ "model.layers.51.post_attention_layernorm": false,
+ "model.layers.52.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.52.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.52.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.52.self_attn.rope": false,
+ "model.layers.52.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.52.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.52.input_layernorm": false,
+ "model.layers.52.post_attention_layernorm": false,
+ "model.layers.53.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.53.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.53.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.53.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.53.self_attn.rope": false,
+ "model.layers.53.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.53.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.53.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.53.input_layernorm": false,
+ "model.layers.53.post_attention_layernorm": false,
+ "model.layers.54.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.54.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.54.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.54.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.54.self_attn.rope": false,
+ "model.layers.54.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.54.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.54.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.54.input_layernorm": false,
+ "model.layers.54.post_attention_layernorm": false,
+ "model.layers.55.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.55.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.55.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.55.self_attn.rope": false,
+ "model.layers.55.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.55.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.55.input_layernorm": false,
+ "model.layers.55.post_attention_layernorm": false,
+ "model.layers.56.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.56.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.56.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.56.self_attn.rope": false,
+ "model.layers.56.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.56.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.56.input_layernorm": false,
+ "model.layers.56.post_attention_layernorm": false,
+ "model.layers.57.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.57.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.57.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.57.self_attn.rope": false,
+ "model.layers.57.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.57.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.57.input_layernorm": false,
+ "model.layers.57.post_attention_layernorm": false,
+ "model.layers.58.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.58.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.58.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.58.self_attn.rope": false,
+ "model.layers.58.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.58.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.58.input_layernorm": false,
+ "model.layers.58.post_attention_layernorm": false,
+ "model.layers.59.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.59.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.59.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.59.self_attn.rope": false,
+ "model.layers.59.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.59.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.59.input_layernorm": false,
+ "model.layers.59.post_attention_layernorm": false,
+ "model.layers.60.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.60.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.60.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.60.self_attn.rope": false,
+ "model.layers.60.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.60.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.60.input_layernorm": false,
+ "model.layers.60.post_attention_layernorm": false,
+ "model.layers.61.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.61.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.61.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.61.self_attn.rope": false,
+ "model.layers.61.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.61.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.61.input_layernorm": false,
+ "model.layers.61.post_attention_layernorm": false,
+ "model.layers.62.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.62.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.62.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.62.self_attn.rope": false,
+ "model.layers.62.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.62.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.62.input_layernorm": false,
+ "model.layers.62.post_attention_layernorm": false,
+ "model.layers.63.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.63.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.63.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.63.self_attn.rope": false,
+ "model.layers.63.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.63.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 2
+ },
+ "model.layers.63.input_layernorm": false,
+ "model.layers.63.post_attention_layernorm": false,
+ "model.norm": false,
+ "lm_head": {
+ "group_size": 64,
+ "bits": 4
+ }
+ },
+ "rms_norm_eps": 1e-05,
+ "rope_theta": 1000000.0,
+ "sliding_window": 131072,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.43.1",
+ "use_cache": true,
+ "use_sliding_window": false,
+ "vocab_size": 152064
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00001-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00001-of-00003.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..525ce1e468c5669bf7eaf2f8b0103414a808e02c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00001-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fd0562b9c91b2672857fdfb6c8f64d34545b54754352a4289ca624a3b51ec7c
+size 5366073812
diff --git a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00002-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00002-of-00003.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e6d0cf8a2604829bbb3f125e8daaa60a66490945
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00002-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cf3baaa2b1173fdade1e377c93b05e81ed99b04d2ac4f19b55fe0d8f7da429e
+size 5303704839
diff --git a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00003-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00003-of-00003.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7d22cc2025e5a4693ce277f4b8489ec0438b060f
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00003-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36559b03cc3bdb442c6e20d45cfe0550b43ba4c1c8bdc1dc9f33aaf4fbb1265b
+size 940057505
diff --git a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..e5a5e26859fcef0de641200508c152d88d92d3d2
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model.safetensors.index.json
@@ -0,0 +1,1678 @@
+{
+ "metadata": {
+ "total_size": 11609647104
+ },
+ "weight_map": {
+ "lm_head.biases": "model-00003-of-00003.safetensors",
+ "lm_head.scales": "model-00003-of-00003.safetensors",
+ "lm_head.weight": "model-00003-of-00003.safetensors",
+ "model.embed_tokens.biases": "model-00001-of-00003.safetensors",
+ "model.embed_tokens.scales": "model-00001-of-00003.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.22.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.22.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.23.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.23.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.23.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.23.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.23.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.23.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.24.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.24.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.24.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.24.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.24.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.24.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.24.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.24.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.24.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.24.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.24.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.24.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.24.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.24.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.25.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.25.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.25.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.25.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.25.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.25.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.25.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.25.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.25.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.25.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.25.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.25.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.25.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.25.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.26.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.26.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.26.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.26.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.26.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.26.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.26.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.26.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.26.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.26.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.26.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.26.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.26.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.26.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.27.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.27.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.27.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.27.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.27.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.27.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.27.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.27.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.27.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.27.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.27.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.27.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.27.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.27.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.28.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.28.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.28.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.28.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.28.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.28.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.28.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.28.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.28.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.28.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.28.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.28.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.28.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.28.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.28.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.28.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.28.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.29.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.29.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.29.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.29.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.29.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.29.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.29.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.29.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.29.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.29.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.29.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.29.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.29.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.29.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.29.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.29.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.29.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.29.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.29.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.40.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.47.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.47.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.47.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.47.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.47.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.47.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.47.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.47.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.47.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.47.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.48.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.48.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.48.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.48.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.48.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.48.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.48.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.48.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.48.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.48.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.48.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.49.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.49.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.49.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.49.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.49.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.49.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.49.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.49.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.49.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.49.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.49.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.49.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.49.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.49.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.49.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.49.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.49.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.49.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.49.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.49.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.49.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.49.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.49.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.49.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.49.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.49.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.50.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.50.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.50.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.50.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.50.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.50.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.50.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.50.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.50.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.50.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.50.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.50.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.50.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.50.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.50.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.50.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.50.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.50.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.50.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.50.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.50.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.50.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.50.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.50.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.50.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.50.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.51.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.51.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.51.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.51.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.51.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.51.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.51.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.51.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.51.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.51.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.51.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.51.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.51.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.51.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.51.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.51.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.51.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.51.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.51.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.51.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.51.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.51.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.51.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.51.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.51.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.51.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.52.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.52.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.52.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.52.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.52.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.52.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.52.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.52.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.52.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.52.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.52.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.52.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.52.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.52.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.52.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.52.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.52.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.52.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.52.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.52.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.52.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.52.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.52.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.52.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.52.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.52.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.53.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.53.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.53.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.53.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.53.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.53.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.53.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.53.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.53.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.53.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.53.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.53.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.53.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.53.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.53.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.53.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.53.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.53.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.53.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.53.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.53.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.53.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.53.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.53.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.53.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.53.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.54.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.54.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.54.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.54.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.54.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.54.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.54.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.54.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.54.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.54.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.54.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.54.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.54.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.54.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.54.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.54.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.54.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.54.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.54.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.54.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.54.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.54.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.54.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.54.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.54.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.54.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.55.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.55.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.55.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.55.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.55.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.55.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.55.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.55.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.55.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.55.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.55.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.55.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.55.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.55.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.55.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.55.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.55.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.55.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.55.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.55.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.55.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.55.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.55.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.55.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.55.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.55.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.56.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.56.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.56.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.56.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.56.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.56.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.56.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.56.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.56.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.56.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.56.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.56.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.56.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.56.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.56.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.56.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.56.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.56.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.56.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.56.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.56.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.56.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.56.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.56.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.56.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.56.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.57.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.57.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.57.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.57.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.57.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.57.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.57.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.57.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.57.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.57.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.57.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.57.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.57.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.57.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.57.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.57.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.57.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.57.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.57.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.57.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.57.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.57.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.57.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.57.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.57.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.57.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.58.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.58.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.58.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.58.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.58.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.58.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.58.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.58.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.58.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.58.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.58.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.58.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.58.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.58.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.58.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.58.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.58.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.58.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.58.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.58.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.58.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.58.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.58.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.58.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.58.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.58.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.59.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.59.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.59.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.59.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.59.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.59.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.59.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.59.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.59.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.59.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.59.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.59.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.59.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.59.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.59.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.59.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.59.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.59.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.59.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.59.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.59.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.59.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.59.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.59.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.59.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.59.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.60.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.60.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.60.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.60.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.60.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.60.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.60.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.60.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.60.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.60.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.60.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.60.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.60.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.60.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.60.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.60.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.60.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.60.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.60.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.60.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.60.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.60.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.60.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.60.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.60.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.60.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.61.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.61.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.61.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.61.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.61.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.61.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.61.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.61.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.61.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.61.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.61.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.61.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.61.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.61.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.61.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.61.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.61.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.61.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.62.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.norm.weight": "model-00003-of-00003.safetensors"
+ }
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/tokenizer_config.json
@@ -0,0 +1,195 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/config.json b/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c25d6bc33782d800fdf5ada7960ebe5c9a778dd5
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/config.json
@@ -0,0 +1,4021 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 5120,
+ "initializer_range": 0.02,
+ "intermediate_size": 27648,
+ "max_position_embeddings": 131072,
+ "max_window_layers": 64,
+ "model_type": "qwen2",
+ "num_attention_heads": 40,
+ "num_hidden_layers": 64,
+ "num_key_value_heads": 8,
+ "quantization": {
+ "group_size": 64,
+ "bits": null,
+ "model.embed_tokens": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.rope": false,
+ "model.layers.0.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.input_layernorm": false,
+ "model.layers.0.post_attention_layernorm": false,
+ "model.layers.1.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.self_attn.rope": false,
+ "model.layers.1.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.input_layernorm": false,
+ "model.layers.1.post_attention_layernorm": false,
+ "model.layers.2.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.self_attn.rope": false,
+ "model.layers.2.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.input_layernorm": false,
+ "model.layers.2.post_attention_layernorm": false,
+ "model.layers.3.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.self_attn.rope": false,
+ "model.layers.3.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.input_layernorm": false,
+ "model.layers.3.post_attention_layernorm": false,
+ "model.layers.4.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.self_attn.rope": false,
+ "model.layers.4.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.input_layernorm": false,
+ "model.layers.4.post_attention_layernorm": false,
+ "model.layers.5.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.self_attn.rope": false,
+ "model.layers.5.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.input_layernorm": false,
+ "model.layers.5.post_attention_layernorm": false,
+ "model.layers.6.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.self_attn.rope": false,
+ "model.layers.6.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.input_layernorm": false,
+ "model.layers.6.post_attention_layernorm": false,
+ "model.layers.7.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.self_attn.rope": false,
+ "model.layers.7.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.input_layernorm": false,
+ "model.layers.7.post_attention_layernorm": false,
+ "model.layers.8.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.self_attn.rope": false,
+ "model.layers.8.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.input_layernorm": false,
+ "model.layers.8.post_attention_layernorm": false,
+ "model.layers.9.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.rope": false,
+ "model.layers.9.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.input_layernorm": false,
+ "model.layers.9.post_attention_layernorm": false,
+ "model.layers.10.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.self_attn.rope": false,
+ "model.layers.10.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.input_layernorm": false,
+ "model.layers.10.post_attention_layernorm": false,
+ "model.layers.11.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.self_attn.rope": false,
+ "model.layers.11.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.input_layernorm": false,
+ "model.layers.11.post_attention_layernorm": false,
+ "model.layers.12.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.rope": false,
+ "model.layers.12.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.input_layernorm": false,
+ "model.layers.12.post_attention_layernorm": false,
+ "model.layers.13.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.self_attn.rope": false,
+ "model.layers.13.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.input_layernorm": false,
+ "model.layers.13.post_attention_layernorm": false,
+ "model.layers.14.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.self_attn.rope": false,
+ "model.layers.14.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.input_layernorm": false,
+ "model.layers.14.post_attention_layernorm": false,
+ "model.layers.15.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.rope": false,
+ "model.layers.15.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.input_layernorm": false,
+ "model.layers.15.post_attention_layernorm": false,
+ "model.layers.16.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.self_attn.rope": false,
+ "model.layers.16.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.input_layernorm": false,
+ "model.layers.16.post_attention_layernorm": false,
+ "model.layers.17.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.self_attn.rope": false,
+ "model.layers.17.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.input_layernorm": false,
+ "model.layers.17.post_attention_layernorm": false,
+ "model.layers.18.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.rope": false,
+ "model.layers.18.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.input_layernorm": false,
+ "model.layers.18.post_attention_layernorm": false,
+ "model.layers.19.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.self_attn.rope": false,
+ "model.layers.19.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.input_layernorm": false,
+ "model.layers.19.post_attention_layernorm": false,
+ "model.layers.20.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.self_attn.rope": false,
+ "model.layers.20.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.input_layernorm": false,
+ "model.layers.20.post_attention_layernorm": false,
+ "model.layers.21.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.rope": false,
+ "model.layers.21.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.input_layernorm": false,
+ "model.layers.21.post_attention_layernorm": false,
+ "model.layers.22.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.self_attn.rope": false,
+ "model.layers.22.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.input_layernorm": false,
+ "model.layers.22.post_attention_layernorm": false,
+ "model.layers.23.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.self_attn.rope": false,
+ "model.layers.23.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.input_layernorm": false,
+ "model.layers.23.post_attention_layernorm": false,
+ "model.layers.24.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.rope": false,
+ "model.layers.24.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.input_layernorm": false,
+ "model.layers.24.post_attention_layernorm": false,
+ "model.layers.25.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.self_attn.rope": false,
+ "model.layers.25.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.input_layernorm": false,
+ "model.layers.25.post_attention_layernorm": false,
+ "model.layers.26.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.self_attn.rope": false,
+ "model.layers.26.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.input_layernorm": false,
+ "model.layers.26.post_attention_layernorm": false,
+ "model.layers.27.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.rope": false,
+ "model.layers.27.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.input_layernorm": false,
+ "model.layers.27.post_attention_layernorm": false,
+ "model.layers.28.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.self_attn.rope": false,
+ "model.layers.28.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.input_layernorm": false,
+ "model.layers.28.post_attention_layernorm": false,
+ "model.layers.29.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.self_attn.rope": false,
+ "model.layers.29.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.input_layernorm": false,
+ "model.layers.29.post_attention_layernorm": false,
+ "model.layers.30.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.rope": false,
+ "model.layers.30.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.input_layernorm": false,
+ "model.layers.30.post_attention_layernorm": false,
+ "model.layers.31.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.self_attn.rope": false,
+ "model.layers.31.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.input_layernorm": false,
+ "model.layers.31.post_attention_layernorm": false,
+ "model.layers.32.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.self_attn.rope": false,
+ "model.layers.32.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.input_layernorm": false,
+ "model.layers.32.post_attention_layernorm": false,
+ "model.layers.33.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.rope": false,
+ "model.layers.33.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.input_layernorm": false,
+ "model.layers.33.post_attention_layernorm": false,
+ "model.layers.34.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.self_attn.rope": false,
+ "model.layers.34.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.input_layernorm": false,
+ "model.layers.34.post_attention_layernorm": false,
+ "model.layers.35.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.self_attn.rope": false,
+ "model.layers.35.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.input_layernorm": false,
+ "model.layers.35.post_attention_layernorm": false,
+ "model.layers.36.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.rope": false,
+ "model.layers.36.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.input_layernorm": false,
+ "model.layers.36.post_attention_layernorm": false,
+ "model.layers.37.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.self_attn.rope": false,
+ "model.layers.37.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.input_layernorm": false,
+ "model.layers.37.post_attention_layernorm": false,
+ "model.layers.38.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.self_attn.rope": false,
+ "model.layers.38.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.input_layernorm": false,
+ "model.layers.38.post_attention_layernorm": false,
+ "model.layers.39.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.rope": false,
+ "model.layers.39.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.input_layernorm": false,
+ "model.layers.39.post_attention_layernorm": false,
+ "model.layers.40.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.self_attn.rope": false,
+ "model.layers.40.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.input_layernorm": false,
+ "model.layers.40.post_attention_layernorm": false,
+ "model.layers.41.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.self_attn.rope": false,
+ "model.layers.41.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.input_layernorm": false,
+ "model.layers.41.post_attention_layernorm": false,
+ "model.layers.42.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.self_attn.rope": false,
+ "model.layers.42.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.input_layernorm": false,
+ "model.layers.42.post_attention_layernorm": false,
+ "model.layers.43.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.self_attn.rope": false,
+ "model.layers.43.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.input_layernorm": false,
+ "model.layers.43.post_attention_layernorm": false,
+ "model.layers.44.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.self_attn.rope": false,
+ "model.layers.44.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.input_layernorm": false,
+ "model.layers.44.post_attention_layernorm": false,
+ "model.layers.45.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.self_attn.rope": false,
+ "model.layers.45.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.input_layernorm": false,
+ "model.layers.45.post_attention_layernorm": false,
+ "model.layers.46.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.self_attn.rope": false,
+ "model.layers.46.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.input_layernorm": false,
+ "model.layers.46.post_attention_layernorm": false,
+ "model.layers.47.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.self_attn.rope": false,
+ "model.layers.47.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.input_layernorm": false,
+ "model.layers.47.post_attention_layernorm": false,
+ "model.layers.48.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.48.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.48.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.48.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.48.self_attn.rope": false,
+ "model.layers.48.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.48.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.48.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.48.input_layernorm": false,
+ "model.layers.48.post_attention_layernorm": false,
+ "model.layers.49.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.49.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.49.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.49.self_attn.rope": false,
+ "model.layers.49.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.49.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.49.input_layernorm": false,
+ "model.layers.49.post_attention_layernorm": false,
+ "model.layers.50.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.50.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.50.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.50.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.50.self_attn.rope": false,
+ "model.layers.50.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.50.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.50.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.50.input_layernorm": false,
+ "model.layers.50.post_attention_layernorm": false,
+ "model.layers.51.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.51.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.51.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.51.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.51.self_attn.rope": false,
+ "model.layers.51.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.51.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.51.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.51.input_layernorm": false,
+ "model.layers.51.post_attention_layernorm": false,
+ "model.layers.52.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.52.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.52.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.52.self_attn.rope": false,
+ "model.layers.52.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.52.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.52.input_layernorm": false,
+ "model.layers.52.post_attention_layernorm": false,
+ "model.layers.53.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.53.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.53.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.53.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.53.self_attn.rope": false,
+ "model.layers.53.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.53.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.53.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.53.input_layernorm": false,
+ "model.layers.53.post_attention_layernorm": false,
+ "model.layers.54.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.54.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.54.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.54.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.54.self_attn.rope": false,
+ "model.layers.54.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.54.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.54.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.54.input_layernorm": false,
+ "model.layers.54.post_attention_layernorm": false,
+ "model.layers.55.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.55.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.55.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.55.self_attn.rope": false,
+ "model.layers.55.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.55.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.55.input_layernorm": false,
+ "model.layers.55.post_attention_layernorm": false,
+ "model.layers.56.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.56.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.56.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.56.self_attn.rope": false,
+ "model.layers.56.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.56.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.56.input_layernorm": false,
+ "model.layers.56.post_attention_layernorm": false,
+ "model.layers.57.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.57.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.57.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.57.self_attn.rope": false,
+ "model.layers.57.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.57.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.57.input_layernorm": false,
+ "model.layers.57.post_attention_layernorm": false,
+ "model.layers.58.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.58.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.58.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.58.self_attn.rope": false,
+ "model.layers.58.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.58.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.58.input_layernorm": false,
+ "model.layers.58.post_attention_layernorm": false,
+ "model.layers.59.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.59.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.59.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.59.self_attn.rope": false,
+ "model.layers.59.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.59.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.59.input_layernorm": false,
+ "model.layers.59.post_attention_layernorm": false,
+ "model.layers.60.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.60.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.60.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.60.self_attn.rope": false,
+ "model.layers.60.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.60.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.60.input_layernorm": false,
+ "model.layers.60.post_attention_layernorm": false,
+ "model.layers.61.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.61.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.61.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.61.self_attn.rope": false,
+ "model.layers.61.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.61.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.61.input_layernorm": false,
+ "model.layers.61.post_attention_layernorm": false,
+ "model.layers.62.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.62.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.62.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.62.self_attn.rope": false,
+ "model.layers.62.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.62.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.62.input_layernorm": false,
+ "model.layers.62.post_attention_layernorm": false,
+ "model.layers.63.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.63.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.63.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.63.self_attn.rope": false,
+ "model.layers.63.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.63.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.63.input_layernorm": false,
+ "model.layers.63.post_attention_layernorm": false,
+ "model.norm": false,
+ "lm_head": {
+ "group_size": 64,
+ "bits": 4
+ }
+ },
+ "quantization_config": {
+ "group_size": 64,
+ "bits": null,
+ "model.embed_tokens": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.rope": false,
+ "model.layers.0.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.input_layernorm": false,
+ "model.layers.0.post_attention_layernorm": false,
+ "model.layers.1.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.self_attn.rope": false,
+ "model.layers.1.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.input_layernorm": false,
+ "model.layers.1.post_attention_layernorm": false,
+ "model.layers.2.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.self_attn.rope": false,
+ "model.layers.2.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.input_layernorm": false,
+ "model.layers.2.post_attention_layernorm": false,
+ "model.layers.3.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.self_attn.rope": false,
+ "model.layers.3.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.input_layernorm": false,
+ "model.layers.3.post_attention_layernorm": false,
+ "model.layers.4.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.self_attn.rope": false,
+ "model.layers.4.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.input_layernorm": false,
+ "model.layers.4.post_attention_layernorm": false,
+ "model.layers.5.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.self_attn.rope": false,
+ "model.layers.5.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.input_layernorm": false,
+ "model.layers.5.post_attention_layernorm": false,
+ "model.layers.6.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.self_attn.rope": false,
+ "model.layers.6.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.input_layernorm": false,
+ "model.layers.6.post_attention_layernorm": false,
+ "model.layers.7.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.self_attn.rope": false,
+ "model.layers.7.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.input_layernorm": false,
+ "model.layers.7.post_attention_layernorm": false,
+ "model.layers.8.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.self_attn.rope": false,
+ "model.layers.8.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.input_layernorm": false,
+ "model.layers.8.post_attention_layernorm": false,
+ "model.layers.9.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.rope": false,
+ "model.layers.9.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.input_layernorm": false,
+ "model.layers.9.post_attention_layernorm": false,
+ "model.layers.10.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.self_attn.rope": false,
+ "model.layers.10.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.input_layernorm": false,
+ "model.layers.10.post_attention_layernorm": false,
+ "model.layers.11.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.self_attn.rope": false,
+ "model.layers.11.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.input_layernorm": false,
+ "model.layers.11.post_attention_layernorm": false,
+ "model.layers.12.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.rope": false,
+ "model.layers.12.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.input_layernorm": false,
+ "model.layers.12.post_attention_layernorm": false,
+ "model.layers.13.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.self_attn.rope": false,
+ "model.layers.13.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.input_layernorm": false,
+ "model.layers.13.post_attention_layernorm": false,
+ "model.layers.14.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.self_attn.rope": false,
+ "model.layers.14.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.input_layernorm": false,
+ "model.layers.14.post_attention_layernorm": false,
+ "model.layers.15.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.rope": false,
+ "model.layers.15.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.input_layernorm": false,
+ "model.layers.15.post_attention_layernorm": false,
+ "model.layers.16.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.self_attn.rope": false,
+ "model.layers.16.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.input_layernorm": false,
+ "model.layers.16.post_attention_layernorm": false,
+ "model.layers.17.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.self_attn.rope": false,
+ "model.layers.17.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.input_layernorm": false,
+ "model.layers.17.post_attention_layernorm": false,
+ "model.layers.18.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.rope": false,
+ "model.layers.18.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.input_layernorm": false,
+ "model.layers.18.post_attention_layernorm": false,
+ "model.layers.19.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.self_attn.rope": false,
+ "model.layers.19.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.input_layernorm": false,
+ "model.layers.19.post_attention_layernorm": false,
+ "model.layers.20.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.self_attn.rope": false,
+ "model.layers.20.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.input_layernorm": false,
+ "model.layers.20.post_attention_layernorm": false,
+ "model.layers.21.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.rope": false,
+ "model.layers.21.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.input_layernorm": false,
+ "model.layers.21.post_attention_layernorm": false,
+ "model.layers.22.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.self_attn.rope": false,
+ "model.layers.22.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.input_layernorm": false,
+ "model.layers.22.post_attention_layernorm": false,
+ "model.layers.23.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.self_attn.rope": false,
+ "model.layers.23.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.input_layernorm": false,
+ "model.layers.23.post_attention_layernorm": false,
+ "model.layers.24.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.rope": false,
+ "model.layers.24.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.input_layernorm": false,
+ "model.layers.24.post_attention_layernorm": false,
+ "model.layers.25.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.self_attn.rope": false,
+ "model.layers.25.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.input_layernorm": false,
+ "model.layers.25.post_attention_layernorm": false,
+ "model.layers.26.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.self_attn.rope": false,
+ "model.layers.26.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.input_layernorm": false,
+ "model.layers.26.post_attention_layernorm": false,
+ "model.layers.27.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.rope": false,
+ "model.layers.27.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.input_layernorm": false,
+ "model.layers.27.post_attention_layernorm": false,
+ "model.layers.28.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.self_attn.rope": false,
+ "model.layers.28.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.input_layernorm": false,
+ "model.layers.28.post_attention_layernorm": false,
+ "model.layers.29.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.self_attn.rope": false,
+ "model.layers.29.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.input_layernorm": false,
+ "model.layers.29.post_attention_layernorm": false,
+ "model.layers.30.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.rope": false,
+ "model.layers.30.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.input_layernorm": false,
+ "model.layers.30.post_attention_layernorm": false,
+ "model.layers.31.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.self_attn.rope": false,
+ "model.layers.31.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.input_layernorm": false,
+ "model.layers.31.post_attention_layernorm": false,
+ "model.layers.32.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.self_attn.rope": false,
+ "model.layers.32.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.input_layernorm": false,
+ "model.layers.32.post_attention_layernorm": false,
+ "model.layers.33.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.rope": false,
+ "model.layers.33.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.input_layernorm": false,
+ "model.layers.33.post_attention_layernorm": false,
+ "model.layers.34.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.self_attn.rope": false,
+ "model.layers.34.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.input_layernorm": false,
+ "model.layers.34.post_attention_layernorm": false,
+ "model.layers.35.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.self_attn.rope": false,
+ "model.layers.35.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.input_layernorm": false,
+ "model.layers.35.post_attention_layernorm": false,
+ "model.layers.36.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.rope": false,
+ "model.layers.36.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.input_layernorm": false,
+ "model.layers.36.post_attention_layernorm": false,
+ "model.layers.37.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.self_attn.rope": false,
+ "model.layers.37.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.input_layernorm": false,
+ "model.layers.37.post_attention_layernorm": false,
+ "model.layers.38.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.self_attn.rope": false,
+ "model.layers.38.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.input_layernorm": false,
+ "model.layers.38.post_attention_layernorm": false,
+ "model.layers.39.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.rope": false,
+ "model.layers.39.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.input_layernorm": false,
+ "model.layers.39.post_attention_layernorm": false,
+ "model.layers.40.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.self_attn.rope": false,
+ "model.layers.40.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.input_layernorm": false,
+ "model.layers.40.post_attention_layernorm": false,
+ "model.layers.41.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.self_attn.rope": false,
+ "model.layers.41.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.input_layernorm": false,
+ "model.layers.41.post_attention_layernorm": false,
+ "model.layers.42.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.self_attn.rope": false,
+ "model.layers.42.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.input_layernorm": false,
+ "model.layers.42.post_attention_layernorm": false,
+ "model.layers.43.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.self_attn.rope": false,
+ "model.layers.43.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.input_layernorm": false,
+ "model.layers.43.post_attention_layernorm": false,
+ "model.layers.44.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.self_attn.rope": false,
+ "model.layers.44.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.input_layernorm": false,
+ "model.layers.44.post_attention_layernorm": false,
+ "model.layers.45.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.self_attn.rope": false,
+ "model.layers.45.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.input_layernorm": false,
+ "model.layers.45.post_attention_layernorm": false,
+ "model.layers.46.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.self_attn.rope": false,
+ "model.layers.46.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.input_layernorm": false,
+ "model.layers.46.post_attention_layernorm": false,
+ "model.layers.47.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.self_attn.rope": false,
+ "model.layers.47.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.input_layernorm": false,
+ "model.layers.47.post_attention_layernorm": false,
+ "model.layers.48.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.48.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.48.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.48.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.48.self_attn.rope": false,
+ "model.layers.48.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.48.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.48.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.48.input_layernorm": false,
+ "model.layers.48.post_attention_layernorm": false,
+ "model.layers.49.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.49.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.49.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.49.self_attn.rope": false,
+ "model.layers.49.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.49.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.49.input_layernorm": false,
+ "model.layers.49.post_attention_layernorm": false,
+ "model.layers.50.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.50.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.50.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.50.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.50.self_attn.rope": false,
+ "model.layers.50.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.50.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.50.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.50.input_layernorm": false,
+ "model.layers.50.post_attention_layernorm": false,
+ "model.layers.51.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.51.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.51.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.51.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.51.self_attn.rope": false,
+ "model.layers.51.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.51.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.51.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.51.input_layernorm": false,
+ "model.layers.51.post_attention_layernorm": false,
+ "model.layers.52.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.52.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.52.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.52.self_attn.rope": false,
+ "model.layers.52.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.52.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.52.input_layernorm": false,
+ "model.layers.52.post_attention_layernorm": false,
+ "model.layers.53.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.53.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.53.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.53.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.53.self_attn.rope": false,
+ "model.layers.53.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.53.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.53.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.53.input_layernorm": false,
+ "model.layers.53.post_attention_layernorm": false,
+ "model.layers.54.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.54.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.54.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.54.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.54.self_attn.rope": false,
+ "model.layers.54.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.54.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.54.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.54.input_layernorm": false,
+ "model.layers.54.post_attention_layernorm": false,
+ "model.layers.55.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.55.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.55.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.55.self_attn.rope": false,
+ "model.layers.55.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.55.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.55.input_layernorm": false,
+ "model.layers.55.post_attention_layernorm": false,
+ "model.layers.56.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.56.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.56.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.56.self_attn.rope": false,
+ "model.layers.56.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.56.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.56.input_layernorm": false,
+ "model.layers.56.post_attention_layernorm": false,
+ "model.layers.57.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.57.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.57.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.57.self_attn.rope": false,
+ "model.layers.57.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.57.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.57.input_layernorm": false,
+ "model.layers.57.post_attention_layernorm": false,
+ "model.layers.58.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.58.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.58.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.58.self_attn.rope": false,
+ "model.layers.58.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.58.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.58.input_layernorm": false,
+ "model.layers.58.post_attention_layernorm": false,
+ "model.layers.59.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.59.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.59.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.59.self_attn.rope": false,
+ "model.layers.59.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.59.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.59.input_layernorm": false,
+ "model.layers.59.post_attention_layernorm": false,
+ "model.layers.60.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.60.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.60.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.60.self_attn.rope": false,
+ "model.layers.60.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.60.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.60.input_layernorm": false,
+ "model.layers.60.post_attention_layernorm": false,
+ "model.layers.61.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.61.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.61.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.61.self_attn.rope": false,
+ "model.layers.61.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.61.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.61.input_layernorm": false,
+ "model.layers.61.post_attention_layernorm": false,
+ "model.layers.62.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.62.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.62.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.62.self_attn.rope": false,
+ "model.layers.62.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.62.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.62.input_layernorm": false,
+ "model.layers.62.post_attention_layernorm": false,
+ "model.layers.63.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.63.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.63.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.63.self_attn.rope": false,
+ "model.layers.63.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.63.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.63.input_layernorm": false,
+ "model.layers.63.post_attention_layernorm": false,
+ "model.norm": false,
+ "lm_head": {
+ "group_size": 64,
+ "bits": 4
+ }
+ },
+ "rms_norm_eps": 1e-05,
+ "rope_theta": 1000000.0,
+ "sliding_window": 131072,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.43.1",
+ "use_cache": true,
+ "use_sliding_window": false,
+ "vocab_size": 152064
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00001-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00001-of-00003.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5e4a46446cb401286042a48927c3e6d3a8bd8c2a
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00001-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1de09b845c5a77c62056128589fa4686507ffb5edda714fe312c24b90edf8648
+size 5344816524
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00002-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00002-of-00003.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3d504b72a810f59628f1d1637fd9480c38887bba
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00002-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86ca2f630b5ee185bd684c721deba18e2728d6939953bd4c7c966af6535ade91
+size 5347005848
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00003-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00003-of-00003.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..03be3f611cefb2ba8b78bce74c8aed0e2e12b420
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00003-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b86b6d4e4db81b48b23f54745d66f94c1878e08d356aaae40aae0ba69f7b48c8
+size 4328835017
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..5894d691559fe9b7406f347a18b89b0b273d9aa7
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model.safetensors.index.json
@@ -0,0 +1,1678 @@
+{
+ "metadata": {
+ "total_size": 15020468224
+ },
+ "weight_map": {
+ "lm_head.biases": "model-00003-of-00003.safetensors",
+ "lm_head.scales": "model-00003-of-00003.safetensors",
+ "lm_head.weight": "model-00003-of-00003.safetensors",
+ "model.embed_tokens.biases": "model-00001-of-00003.safetensors",
+ "model.embed_tokens.scales": "model-00001-of-00003.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.40.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.46.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.46.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.46.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.47.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.48.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.48.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.48.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.48.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.48.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.48.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.48.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.48.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.48.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.48.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.48.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.49.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.49.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.49.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.49.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.49.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.49.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.49.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.49.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.49.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.49.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.49.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.50.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.50.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.50.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.50.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.50.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.50.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.50.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.50.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.50.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.50.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.50.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.51.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.51.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.51.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.51.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.51.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.51.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.51.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.51.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.51.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.51.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.51.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.52.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.52.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.52.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.52.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.52.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.52.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.52.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.52.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.52.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.52.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.52.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.53.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.53.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.53.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.53.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.53.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.53.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.53.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.53.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.53.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.53.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.53.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.54.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.54.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.54.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.54.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.54.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.54.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.54.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.54.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.54.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.54.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.54.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.55.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.55.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.55.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.55.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.55.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.55.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.55.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.55.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.55.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.55.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.55.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.56.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.56.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.56.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.56.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.56.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.56.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.56.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.56.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.56.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.56.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.56.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.57.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.57.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.57.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.57.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.57.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.57.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.57.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.57.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.57.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.57.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.57.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.58.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.58.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.58.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.58.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.58.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.58.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.58.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.58.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.58.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.58.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.58.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.59.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.59.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.59.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.59.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.59.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.59.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.59.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.59.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.59.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.59.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.59.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.60.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.60.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.60.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.60.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.60.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.60.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.60.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.60.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.60.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.60.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.60.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.norm.weight": "model-00003-of-00003.safetensors"
+ }
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/tokenizer_config.json
@@ -0,0 +1,195 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/config.json b/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c25d6bc33782d800fdf5ada7960ebe5c9a778dd5
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/config.json
@@ -0,0 +1,4021 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 5120,
+ "initializer_range": 0.02,
+ "intermediate_size": 27648,
+ "max_position_embeddings": 131072,
+ "max_window_layers": 64,
+ "model_type": "qwen2",
+ "num_attention_heads": 40,
+ "num_hidden_layers": 64,
+ "num_key_value_heads": 8,
+ "quantization": {
+ "group_size": 64,
+ "bits": null,
+ "model.embed_tokens": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.rope": false,
+ "model.layers.0.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.input_layernorm": false,
+ "model.layers.0.post_attention_layernorm": false,
+ "model.layers.1.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.self_attn.rope": false,
+ "model.layers.1.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.input_layernorm": false,
+ "model.layers.1.post_attention_layernorm": false,
+ "model.layers.2.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.self_attn.rope": false,
+ "model.layers.2.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.input_layernorm": false,
+ "model.layers.2.post_attention_layernorm": false,
+ "model.layers.3.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.self_attn.rope": false,
+ "model.layers.3.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.input_layernorm": false,
+ "model.layers.3.post_attention_layernorm": false,
+ "model.layers.4.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.self_attn.rope": false,
+ "model.layers.4.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.input_layernorm": false,
+ "model.layers.4.post_attention_layernorm": false,
+ "model.layers.5.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.self_attn.rope": false,
+ "model.layers.5.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.input_layernorm": false,
+ "model.layers.5.post_attention_layernorm": false,
+ "model.layers.6.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.self_attn.rope": false,
+ "model.layers.6.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.input_layernorm": false,
+ "model.layers.6.post_attention_layernorm": false,
+ "model.layers.7.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.self_attn.rope": false,
+ "model.layers.7.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.input_layernorm": false,
+ "model.layers.7.post_attention_layernorm": false,
+ "model.layers.8.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.self_attn.rope": false,
+ "model.layers.8.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.input_layernorm": false,
+ "model.layers.8.post_attention_layernorm": false,
+ "model.layers.9.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.rope": false,
+ "model.layers.9.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.input_layernorm": false,
+ "model.layers.9.post_attention_layernorm": false,
+ "model.layers.10.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.self_attn.rope": false,
+ "model.layers.10.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.input_layernorm": false,
+ "model.layers.10.post_attention_layernorm": false,
+ "model.layers.11.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.self_attn.rope": false,
+ "model.layers.11.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.input_layernorm": false,
+ "model.layers.11.post_attention_layernorm": false,
+ "model.layers.12.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.rope": false,
+ "model.layers.12.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.input_layernorm": false,
+ "model.layers.12.post_attention_layernorm": false,
+ "model.layers.13.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.self_attn.rope": false,
+ "model.layers.13.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.input_layernorm": false,
+ "model.layers.13.post_attention_layernorm": false,
+ "model.layers.14.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.self_attn.rope": false,
+ "model.layers.14.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.input_layernorm": false,
+ "model.layers.14.post_attention_layernorm": false,
+ "model.layers.15.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.rope": false,
+ "model.layers.15.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.input_layernorm": false,
+ "model.layers.15.post_attention_layernorm": false,
+ "model.layers.16.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.self_attn.rope": false,
+ "model.layers.16.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.input_layernorm": false,
+ "model.layers.16.post_attention_layernorm": false,
+ "model.layers.17.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.self_attn.rope": false,
+ "model.layers.17.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.input_layernorm": false,
+ "model.layers.17.post_attention_layernorm": false,
+ "model.layers.18.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.rope": false,
+ "model.layers.18.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.input_layernorm": false,
+ "model.layers.18.post_attention_layernorm": false,
+ "model.layers.19.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.self_attn.rope": false,
+ "model.layers.19.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.input_layernorm": false,
+ "model.layers.19.post_attention_layernorm": false,
+ "model.layers.20.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.self_attn.rope": false,
+ "model.layers.20.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.input_layernorm": false,
+ "model.layers.20.post_attention_layernorm": false,
+ "model.layers.21.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.rope": false,
+ "model.layers.21.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.input_layernorm": false,
+ "model.layers.21.post_attention_layernorm": false,
+ "model.layers.22.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.self_attn.rope": false,
+ "model.layers.22.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.input_layernorm": false,
+ "model.layers.22.post_attention_layernorm": false,
+ "model.layers.23.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.self_attn.rope": false,
+ "model.layers.23.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.input_layernorm": false,
+ "model.layers.23.post_attention_layernorm": false,
+ "model.layers.24.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.rope": false,
+ "model.layers.24.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.input_layernorm": false,
+ "model.layers.24.post_attention_layernorm": false,
+ "model.layers.25.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.self_attn.rope": false,
+ "model.layers.25.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.input_layernorm": false,
+ "model.layers.25.post_attention_layernorm": false,
+ "model.layers.26.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.self_attn.rope": false,
+ "model.layers.26.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.input_layernorm": false,
+ "model.layers.26.post_attention_layernorm": false,
+ "model.layers.27.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.rope": false,
+ "model.layers.27.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.input_layernorm": false,
+ "model.layers.27.post_attention_layernorm": false,
+ "model.layers.28.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.self_attn.rope": false,
+ "model.layers.28.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.input_layernorm": false,
+ "model.layers.28.post_attention_layernorm": false,
+ "model.layers.29.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.self_attn.rope": false,
+ "model.layers.29.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.input_layernorm": false,
+ "model.layers.29.post_attention_layernorm": false,
+ "model.layers.30.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.rope": false,
+ "model.layers.30.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.input_layernorm": false,
+ "model.layers.30.post_attention_layernorm": false,
+ "model.layers.31.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.self_attn.rope": false,
+ "model.layers.31.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.input_layernorm": false,
+ "model.layers.31.post_attention_layernorm": false,
+ "model.layers.32.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.self_attn.rope": false,
+ "model.layers.32.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.input_layernorm": false,
+ "model.layers.32.post_attention_layernorm": false,
+ "model.layers.33.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.rope": false,
+ "model.layers.33.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.input_layernorm": false,
+ "model.layers.33.post_attention_layernorm": false,
+ "model.layers.34.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.self_attn.rope": false,
+ "model.layers.34.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.input_layernorm": false,
+ "model.layers.34.post_attention_layernorm": false,
+ "model.layers.35.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.self_attn.rope": false,
+ "model.layers.35.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.input_layernorm": false,
+ "model.layers.35.post_attention_layernorm": false,
+ "model.layers.36.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.rope": false,
+ "model.layers.36.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.input_layernorm": false,
+ "model.layers.36.post_attention_layernorm": false,
+ "model.layers.37.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.self_attn.rope": false,
+ "model.layers.37.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.input_layernorm": false,
+ "model.layers.37.post_attention_layernorm": false,
+ "model.layers.38.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.self_attn.rope": false,
+ "model.layers.38.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.input_layernorm": false,
+ "model.layers.38.post_attention_layernorm": false,
+ "model.layers.39.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.rope": false,
+ "model.layers.39.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.input_layernorm": false,
+ "model.layers.39.post_attention_layernorm": false,
+ "model.layers.40.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.self_attn.rope": false,
+ "model.layers.40.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.input_layernorm": false,
+ "model.layers.40.post_attention_layernorm": false,
+ "model.layers.41.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.self_attn.rope": false,
+ "model.layers.41.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.input_layernorm": false,
+ "model.layers.41.post_attention_layernorm": false,
+ "model.layers.42.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.self_attn.rope": false,
+ "model.layers.42.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.input_layernorm": false,
+ "model.layers.42.post_attention_layernorm": false,
+ "model.layers.43.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.self_attn.rope": false,
+ "model.layers.43.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.input_layernorm": false,
+ "model.layers.43.post_attention_layernorm": false,
+ "model.layers.44.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.self_attn.rope": false,
+ "model.layers.44.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.input_layernorm": false,
+ "model.layers.44.post_attention_layernorm": false,
+ "model.layers.45.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.self_attn.rope": false,
+ "model.layers.45.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.input_layernorm": false,
+ "model.layers.45.post_attention_layernorm": false,
+ "model.layers.46.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.self_attn.rope": false,
+ "model.layers.46.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.input_layernorm": false,
+ "model.layers.46.post_attention_layernorm": false,
+ "model.layers.47.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.self_attn.rope": false,
+ "model.layers.47.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.input_layernorm": false,
+ "model.layers.47.post_attention_layernorm": false,
+ "model.layers.48.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.48.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.48.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.48.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.48.self_attn.rope": false,
+ "model.layers.48.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.48.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.48.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.48.input_layernorm": false,
+ "model.layers.48.post_attention_layernorm": false,
+ "model.layers.49.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.49.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.49.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.49.self_attn.rope": false,
+ "model.layers.49.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.49.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.49.input_layernorm": false,
+ "model.layers.49.post_attention_layernorm": false,
+ "model.layers.50.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.50.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.50.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.50.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.50.self_attn.rope": false,
+ "model.layers.50.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.50.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.50.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.50.input_layernorm": false,
+ "model.layers.50.post_attention_layernorm": false,
+ "model.layers.51.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.51.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.51.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.51.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.51.self_attn.rope": false,
+ "model.layers.51.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.51.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.51.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.51.input_layernorm": false,
+ "model.layers.51.post_attention_layernorm": false,
+ "model.layers.52.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.52.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.52.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.52.self_attn.rope": false,
+ "model.layers.52.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.52.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.52.input_layernorm": false,
+ "model.layers.52.post_attention_layernorm": false,
+ "model.layers.53.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.53.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.53.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.53.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.53.self_attn.rope": false,
+ "model.layers.53.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.53.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.53.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.53.input_layernorm": false,
+ "model.layers.53.post_attention_layernorm": false,
+ "model.layers.54.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.54.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.54.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.54.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.54.self_attn.rope": false,
+ "model.layers.54.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.54.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.54.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.54.input_layernorm": false,
+ "model.layers.54.post_attention_layernorm": false,
+ "model.layers.55.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.55.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.55.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.55.self_attn.rope": false,
+ "model.layers.55.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.55.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.55.input_layernorm": false,
+ "model.layers.55.post_attention_layernorm": false,
+ "model.layers.56.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.56.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.56.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.56.self_attn.rope": false,
+ "model.layers.56.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.56.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.56.input_layernorm": false,
+ "model.layers.56.post_attention_layernorm": false,
+ "model.layers.57.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.57.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.57.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.57.self_attn.rope": false,
+ "model.layers.57.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.57.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.57.input_layernorm": false,
+ "model.layers.57.post_attention_layernorm": false,
+ "model.layers.58.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.58.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.58.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.58.self_attn.rope": false,
+ "model.layers.58.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.58.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.58.input_layernorm": false,
+ "model.layers.58.post_attention_layernorm": false,
+ "model.layers.59.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.59.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.59.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.59.self_attn.rope": false,
+ "model.layers.59.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.59.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.59.input_layernorm": false,
+ "model.layers.59.post_attention_layernorm": false,
+ "model.layers.60.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.60.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.60.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.60.self_attn.rope": false,
+ "model.layers.60.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.60.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.60.input_layernorm": false,
+ "model.layers.60.post_attention_layernorm": false,
+ "model.layers.61.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.61.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.61.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.61.self_attn.rope": false,
+ "model.layers.61.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.61.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.61.input_layernorm": false,
+ "model.layers.61.post_attention_layernorm": false,
+ "model.layers.62.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.62.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.62.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.62.self_attn.rope": false,
+ "model.layers.62.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.62.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.62.input_layernorm": false,
+ "model.layers.62.post_attention_layernorm": false,
+ "model.layers.63.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.63.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.63.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.63.self_attn.rope": false,
+ "model.layers.63.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.63.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.63.input_layernorm": false,
+ "model.layers.63.post_attention_layernorm": false,
+ "model.norm": false,
+ "lm_head": {
+ "group_size": 64,
+ "bits": 4
+ }
+ },
+ "quantization_config": {
+ "group_size": 64,
+ "bits": null,
+ "model.embed_tokens": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.self_attn.rope": false,
+ "model.layers.0.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.0.input_layernorm": false,
+ "model.layers.0.post_attention_layernorm": false,
+ "model.layers.1.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.self_attn.rope": false,
+ "model.layers.1.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.1.input_layernorm": false,
+ "model.layers.1.post_attention_layernorm": false,
+ "model.layers.2.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.self_attn.rope": false,
+ "model.layers.2.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.2.input_layernorm": false,
+ "model.layers.2.post_attention_layernorm": false,
+ "model.layers.3.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.self_attn.rope": false,
+ "model.layers.3.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.3.input_layernorm": false,
+ "model.layers.3.post_attention_layernorm": false,
+ "model.layers.4.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.self_attn.rope": false,
+ "model.layers.4.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.4.input_layernorm": false,
+ "model.layers.4.post_attention_layernorm": false,
+ "model.layers.5.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.self_attn.rope": false,
+ "model.layers.5.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.5.input_layernorm": false,
+ "model.layers.5.post_attention_layernorm": false,
+ "model.layers.6.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.self_attn.rope": false,
+ "model.layers.6.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.6.input_layernorm": false,
+ "model.layers.6.post_attention_layernorm": false,
+ "model.layers.7.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.self_attn.rope": false,
+ "model.layers.7.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.7.input_layernorm": false,
+ "model.layers.7.post_attention_layernorm": false,
+ "model.layers.8.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.self_attn.rope": false,
+ "model.layers.8.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.8.input_layernorm": false,
+ "model.layers.8.post_attention_layernorm": false,
+ "model.layers.9.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.self_attn.rope": false,
+ "model.layers.9.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.9.input_layernorm": false,
+ "model.layers.9.post_attention_layernorm": false,
+ "model.layers.10.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.self_attn.rope": false,
+ "model.layers.10.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.10.input_layernorm": false,
+ "model.layers.10.post_attention_layernorm": false,
+ "model.layers.11.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.self_attn.rope": false,
+ "model.layers.11.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.11.input_layernorm": false,
+ "model.layers.11.post_attention_layernorm": false,
+ "model.layers.12.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.self_attn.rope": false,
+ "model.layers.12.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.12.input_layernorm": false,
+ "model.layers.12.post_attention_layernorm": false,
+ "model.layers.13.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.self_attn.rope": false,
+ "model.layers.13.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.13.input_layernorm": false,
+ "model.layers.13.post_attention_layernorm": false,
+ "model.layers.14.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.self_attn.rope": false,
+ "model.layers.14.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.14.input_layernorm": false,
+ "model.layers.14.post_attention_layernorm": false,
+ "model.layers.15.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.self_attn.rope": false,
+ "model.layers.15.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.15.input_layernorm": false,
+ "model.layers.15.post_attention_layernorm": false,
+ "model.layers.16.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.self_attn.rope": false,
+ "model.layers.16.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.16.input_layernorm": false,
+ "model.layers.16.post_attention_layernorm": false,
+ "model.layers.17.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.self_attn.rope": false,
+ "model.layers.17.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.17.input_layernorm": false,
+ "model.layers.17.post_attention_layernorm": false,
+ "model.layers.18.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.self_attn.rope": false,
+ "model.layers.18.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.18.input_layernorm": false,
+ "model.layers.18.post_attention_layernorm": false,
+ "model.layers.19.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.self_attn.rope": false,
+ "model.layers.19.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.19.input_layernorm": false,
+ "model.layers.19.post_attention_layernorm": false,
+ "model.layers.20.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.self_attn.rope": false,
+ "model.layers.20.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.20.input_layernorm": false,
+ "model.layers.20.post_attention_layernorm": false,
+ "model.layers.21.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.self_attn.rope": false,
+ "model.layers.21.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.21.input_layernorm": false,
+ "model.layers.21.post_attention_layernorm": false,
+ "model.layers.22.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.self_attn.rope": false,
+ "model.layers.22.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.22.input_layernorm": false,
+ "model.layers.22.post_attention_layernorm": false,
+ "model.layers.23.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.self_attn.rope": false,
+ "model.layers.23.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.23.input_layernorm": false,
+ "model.layers.23.post_attention_layernorm": false,
+ "model.layers.24.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.self_attn.rope": false,
+ "model.layers.24.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.24.input_layernorm": false,
+ "model.layers.24.post_attention_layernorm": false,
+ "model.layers.25.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.self_attn.rope": false,
+ "model.layers.25.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.25.input_layernorm": false,
+ "model.layers.25.post_attention_layernorm": false,
+ "model.layers.26.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.self_attn.rope": false,
+ "model.layers.26.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.26.input_layernorm": false,
+ "model.layers.26.post_attention_layernorm": false,
+ "model.layers.27.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.self_attn.rope": false,
+ "model.layers.27.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.27.input_layernorm": false,
+ "model.layers.27.post_attention_layernorm": false,
+ "model.layers.28.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.self_attn.rope": false,
+ "model.layers.28.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.28.input_layernorm": false,
+ "model.layers.28.post_attention_layernorm": false,
+ "model.layers.29.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.self_attn.rope": false,
+ "model.layers.29.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.29.input_layernorm": false,
+ "model.layers.29.post_attention_layernorm": false,
+ "model.layers.30.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.self_attn.rope": false,
+ "model.layers.30.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.30.input_layernorm": false,
+ "model.layers.30.post_attention_layernorm": false,
+ "model.layers.31.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.self_attn.rope": false,
+ "model.layers.31.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.31.input_layernorm": false,
+ "model.layers.31.post_attention_layernorm": false,
+ "model.layers.32.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.self_attn.rope": false,
+ "model.layers.32.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.32.input_layernorm": false,
+ "model.layers.32.post_attention_layernorm": false,
+ "model.layers.33.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.self_attn.rope": false,
+ "model.layers.33.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.33.input_layernorm": false,
+ "model.layers.33.post_attention_layernorm": false,
+ "model.layers.34.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.self_attn.rope": false,
+ "model.layers.34.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.34.input_layernorm": false,
+ "model.layers.34.post_attention_layernorm": false,
+ "model.layers.35.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.self_attn.rope": false,
+ "model.layers.35.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.35.input_layernorm": false,
+ "model.layers.35.post_attention_layernorm": false,
+ "model.layers.36.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.self_attn.rope": false,
+ "model.layers.36.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.36.input_layernorm": false,
+ "model.layers.36.post_attention_layernorm": false,
+ "model.layers.37.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.self_attn.rope": false,
+ "model.layers.37.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.37.input_layernorm": false,
+ "model.layers.37.post_attention_layernorm": false,
+ "model.layers.38.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.self_attn.rope": false,
+ "model.layers.38.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.38.input_layernorm": false,
+ "model.layers.38.post_attention_layernorm": false,
+ "model.layers.39.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.self_attn.rope": false,
+ "model.layers.39.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.39.input_layernorm": false,
+ "model.layers.39.post_attention_layernorm": false,
+ "model.layers.40.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.self_attn.rope": false,
+ "model.layers.40.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.40.input_layernorm": false,
+ "model.layers.40.post_attention_layernorm": false,
+ "model.layers.41.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.self_attn.rope": false,
+ "model.layers.41.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.41.input_layernorm": false,
+ "model.layers.41.post_attention_layernorm": false,
+ "model.layers.42.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.self_attn.rope": false,
+ "model.layers.42.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.42.input_layernorm": false,
+ "model.layers.42.post_attention_layernorm": false,
+ "model.layers.43.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.self_attn.rope": false,
+ "model.layers.43.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.43.input_layernorm": false,
+ "model.layers.43.post_attention_layernorm": false,
+ "model.layers.44.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.self_attn.rope": false,
+ "model.layers.44.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.44.input_layernorm": false,
+ "model.layers.44.post_attention_layernorm": false,
+ "model.layers.45.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.self_attn.rope": false,
+ "model.layers.45.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.45.input_layernorm": false,
+ "model.layers.45.post_attention_layernorm": false,
+ "model.layers.46.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.self_attn.rope": false,
+ "model.layers.46.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.46.input_layernorm": false,
+ "model.layers.46.post_attention_layernorm": false,
+ "model.layers.47.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.self_attn.rope": false,
+ "model.layers.47.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.47.input_layernorm": false,
+ "model.layers.47.post_attention_layernorm": false,
+ "model.layers.48.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.48.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.48.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.48.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.48.self_attn.rope": false,
+ "model.layers.48.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.48.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.48.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.48.input_layernorm": false,
+ "model.layers.48.post_attention_layernorm": false,
+ "model.layers.49.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.49.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.49.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.49.self_attn.rope": false,
+ "model.layers.49.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.49.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.49.input_layernorm": false,
+ "model.layers.49.post_attention_layernorm": false,
+ "model.layers.50.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.50.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.50.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.50.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.50.self_attn.rope": false,
+ "model.layers.50.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.50.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.50.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.50.input_layernorm": false,
+ "model.layers.50.post_attention_layernorm": false,
+ "model.layers.51.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.51.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.51.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.51.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.51.self_attn.rope": false,
+ "model.layers.51.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.51.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.51.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.51.input_layernorm": false,
+ "model.layers.51.post_attention_layernorm": false,
+ "model.layers.52.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.52.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.52.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.52.self_attn.rope": false,
+ "model.layers.52.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.52.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.52.input_layernorm": false,
+ "model.layers.52.post_attention_layernorm": false,
+ "model.layers.53.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.53.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.53.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.53.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.53.self_attn.rope": false,
+ "model.layers.53.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.53.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.53.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.53.input_layernorm": false,
+ "model.layers.53.post_attention_layernorm": false,
+ "model.layers.54.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.54.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.54.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.54.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.54.self_attn.rope": false,
+ "model.layers.54.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.54.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.54.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.54.input_layernorm": false,
+ "model.layers.54.post_attention_layernorm": false,
+ "model.layers.55.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.55.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.55.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.55.self_attn.rope": false,
+ "model.layers.55.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.55.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.55.input_layernorm": false,
+ "model.layers.55.post_attention_layernorm": false,
+ "model.layers.56.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.56.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.56.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.56.self_attn.rope": false,
+ "model.layers.56.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.56.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.56.input_layernorm": false,
+ "model.layers.56.post_attention_layernorm": false,
+ "model.layers.57.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.57.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.57.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.57.self_attn.rope": false,
+ "model.layers.57.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.57.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.57.input_layernorm": false,
+ "model.layers.57.post_attention_layernorm": false,
+ "model.layers.58.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.58.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.58.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.58.self_attn.rope": false,
+ "model.layers.58.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.58.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.58.input_layernorm": false,
+ "model.layers.58.post_attention_layernorm": false,
+ "model.layers.59.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.59.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.59.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.59.self_attn.rope": false,
+ "model.layers.59.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.59.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.59.input_layernorm": false,
+ "model.layers.59.post_attention_layernorm": false,
+ "model.layers.60.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.60.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.60.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.60.self_attn.rope": false,
+ "model.layers.60.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.60.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.60.input_layernorm": false,
+ "model.layers.60.post_attention_layernorm": false,
+ "model.layers.61.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.61.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.61.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.61.self_attn.rope": false,
+ "model.layers.61.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.61.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.61.input_layernorm": false,
+ "model.layers.61.post_attention_layernorm": false,
+ "model.layers.62.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.62.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.62.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.62.self_attn.rope": false,
+ "model.layers.62.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.62.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.62.input_layernorm": false,
+ "model.layers.62.post_attention_layernorm": false,
+ "model.layers.63.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.63.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.63.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.63.self_attn.rope": false,
+ "model.layers.63.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.63.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "model.layers.63.input_layernorm": false,
+ "model.layers.63.post_attention_layernorm": false,
+ "model.norm": false,
+ "lm_head": {
+ "group_size": 64,
+ "bits": 4
+ }
+ },
+ "rms_norm_eps": 1e-05,
+ "rope_theta": 1000000.0,
+ "sliding_window": 131072,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.43.1",
+ "use_cache": true,
+ "use_sliding_window": false,
+ "vocab_size": 152064
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00001-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00001-of-00003.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5e4a46446cb401286042a48927c3e6d3a8bd8c2a
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00001-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1de09b845c5a77c62056128589fa4686507ffb5edda714fe312c24b90edf8648
+size 5344816524
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00002-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00002-of-00003.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3d504b72a810f59628f1d1637fd9480c38887bba
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00002-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86ca2f630b5ee185bd684c721deba18e2728d6939953bd4c7c966af6535ade91
+size 5347005848
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00003-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00003-of-00003.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..03be3f611cefb2ba8b78bce74c8aed0e2e12b420
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00003-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b86b6d4e4db81b48b23f54745d66f94c1878e08d356aaae40aae0ba69f7b48c8
+size 4328835017
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..5894d691559fe9b7406f347a18b89b0b273d9aa7
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model.safetensors.index.json
@@ -0,0 +1,1678 @@
+{
+ "metadata": {
+ "total_size": 15020468224
+ },
+ "weight_map": {
+ "lm_head.biases": "model-00003-of-00003.safetensors",
+ "lm_head.scales": "model-00003-of-00003.safetensors",
+ "lm_head.weight": "model-00003-of-00003.safetensors",
+ "model.embed_tokens.biases": "model-00001-of-00003.safetensors",
+ "model.embed_tokens.scales": "model-00001-of-00003.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.40.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.46.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.46.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.46.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.46.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.47.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.47.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.47.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.48.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.48.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.48.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.48.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.48.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.48.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.48.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.48.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.48.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.48.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.48.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.49.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.49.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.49.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.49.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.49.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.49.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.49.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.49.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.49.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.49.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.49.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.50.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.50.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.50.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.50.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.50.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.50.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.50.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.50.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.50.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.50.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.50.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.51.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.51.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.51.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.51.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.51.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.51.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.51.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.51.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.51.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.51.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.51.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.52.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.52.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.52.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.52.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.52.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.52.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.52.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.52.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.52.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.52.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.52.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.53.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.53.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.53.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.53.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.53.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.53.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.53.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.53.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.53.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.53.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.53.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.54.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.54.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.54.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.54.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.54.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.54.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.54.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.54.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.54.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.54.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.54.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.55.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.55.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.55.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.55.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.55.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.55.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.55.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.55.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.55.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.55.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.55.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.56.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.56.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.56.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.56.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.56.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.56.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.56.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.56.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.56.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.56.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.56.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.57.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.57.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.57.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.57.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.57.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.57.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.57.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.57.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.57.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.57.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.57.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.58.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.58.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.58.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.58.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.58.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.58.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.58.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.58.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.58.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.58.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.58.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.59.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.59.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.59.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.59.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.59.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.59.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.59.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.59.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.59.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.59.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.59.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.60.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.60.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.60.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.60.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.60.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.60.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.60.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.60.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.60.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.60.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.60.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.norm.weight": "model-00003-of-00003.safetensors"
+ }
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/tokenizer_config.json
@@ -0,0 +1,195 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3bit/config.json b/DeepSeek-R1-Distill-Qwen-32B-3bit/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..7d7ebe2eb98861da258a639106462a672a45dc19
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-3bit/config.json
@@ -0,0 +1,35 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 5120,
+ "initializer_range": 0.02,
+ "intermediate_size": 27648,
+ "max_position_embeddings": 131072,
+ "max_window_layers": 64,
+ "model_type": "qwen2",
+ "num_attention_heads": 40,
+ "num_hidden_layers": 64,
+ "num_key_value_heads": 8,
+ "quantization": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "quantization_config": {
+ "group_size": 64,
+ "bits": 3
+ },
+ "rms_norm_eps": 1e-05,
+ "rope_theta": 1000000.0,
+ "sliding_window": 131072,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.43.1",
+ "use_cache": true,
+ "use_sliding_window": false,
+ "vocab_size": 152064
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3bit/model-00001-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B-3bit/model-00001-of-00003.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..55a719b6fb705f3879d168a1169b7bede9b45a75
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-3bit/model-00001-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df28fc49354643e4296ed66bccf6526153a646ad35a9419981d0910ab6bbc135
+size 5337317621
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3bit/model-00002-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B-3bit/model-00002-of-00003.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fec208e035af0faf2a3597b17dc4e0c7c48f32df
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-3bit/model-00002-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec2df739f0f8748043700a3654acd764a9e0e613d7a8927a80ee39d1a08cef24
+size 5333936095
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3bit/model-00003-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B-3bit/model-00003-of-00003.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ec71156413e33dfc3e1e31e7eb09e3015d8c0100
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-3bit/model-00003-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:163ab92116e3a30ff1196343de0559f39f90211cb8e0b30a78727cc57d712597
+size 3664880049
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3bit/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B-3bit/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..0ecaad16f85e981118dfea7127056660adf05a44
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-3bit/model.safetensors.index.json
@@ -0,0 +1,1678 @@
+{
+ "metadata": {
+ "total_size": 14335944704
+ },
+ "weight_map": {
+ "lm_head.biases": "model-00003-of-00003.safetensors",
+ "lm_head.scales": "model-00003-of-00003.safetensors",
+ "lm_head.weight": "model-00003-of-00003.safetensors",
+ "model.embed_tokens.biases": "model-00001-of-00003.safetensors",
+ "model.embed_tokens.scales": "model-00001-of-00003.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.22.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.22.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.23.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.23.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.40.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.46.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.47.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.47.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.47.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.47.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.47.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.47.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.47.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.47.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.47.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.47.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.47.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.48.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.48.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.48.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.48.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.48.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.48.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.48.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.48.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.48.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.48.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.48.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.48.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+ "model.layers.48.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.49.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.49.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.49.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.49.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.49.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.49.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.49.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.49.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.49.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.49.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.49.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.49.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.50.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.50.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.50.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.50.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.50.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.50.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.50.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.50.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.50.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.50.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.50.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.50.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.51.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.51.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.51.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.51.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.51.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.51.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.51.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.51.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.51.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.51.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.51.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.51.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.52.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.52.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.52.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.52.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.52.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.52.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.52.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.52.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.52.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.52.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.52.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.52.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.53.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.53.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.53.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.53.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.53.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.53.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.53.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.53.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.53.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.53.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.53.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.53.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.54.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.54.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.54.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.54.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.54.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.54.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.54.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.54.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.54.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.54.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.54.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.54.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.55.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.55.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.55.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.55.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.55.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.55.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.55.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.55.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.55.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.55.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.55.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.55.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.56.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.56.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.56.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.56.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.56.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.56.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.56.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.56.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.56.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.56.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.56.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.56.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.57.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.57.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.57.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.57.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.57.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.57.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.57.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.57.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.57.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.57.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.57.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.57.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.58.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.58.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.58.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.58.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.58.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.58.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.58.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.58.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.58.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.58.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.58.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.58.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.59.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.59.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.59.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.59.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.59.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.59.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.59.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.59.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.59.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.59.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.59.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.59.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.60.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.60.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.60.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.60.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.60.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.60.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.60.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.60.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.60.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.60.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.60.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.60.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.61.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.61.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.62.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.62.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.63.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+ "model.layers.63.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.norm.weight": "model-00003-of-00003.safetensors"
+ }
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3bit/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B-3bit/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-3bit/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3bit/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B-3bit/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-3bit/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-32B-3bit/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B-3bit/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-3bit/tokenizer_config.json
@@ -0,0 +1,195 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/config.json b/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..4b4b9dfd75e58ed26066589c787bf65e9666ddba
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/config.json
@@ -0,0 +1,4021 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 5120,
+ "initializer_range": 0.02,
+ "intermediate_size": 27648,
+ "max_position_embeddings": 131072,
+ "max_window_layers": 64,
+ "model_type": "qwen2",
+ "num_attention_heads": 40,
+ "num_hidden_layers": 64,
+ "num_key_value_heads": 8,
+ "quantization": {
+ "group_size": 64,
+ "bits": null,
+ "model.embed_tokens": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.0.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.rope": false,
+ "model.layers.0.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.0.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.input_layernorm": false,
+ "model.layers.0.post_attention_layernorm": false,
+ "model.layers.1.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.1.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.rope": false,
+ "model.layers.1.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.1.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.input_layernorm": false,
+ "model.layers.1.post_attention_layernorm": false,
+ "model.layers.2.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.2.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.rope": false,
+ "model.layers.2.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.2.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.input_layernorm": false,
+ "model.layers.2.post_attention_layernorm": false,
+ "model.layers.3.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.3.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.rope": false,
+ "model.layers.3.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.3.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.input_layernorm": false,
+ "model.layers.3.post_attention_layernorm": false,
+ "model.layers.4.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.4.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.rope": false,
+ "model.layers.4.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.4.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.input_layernorm": false,
+ "model.layers.4.post_attention_layernorm": false,
+ "model.layers.5.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.5.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.rope": false,
+ "model.layers.5.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.5.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.input_layernorm": false,
+ "model.layers.5.post_attention_layernorm": false,
+ "model.layers.6.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.6.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.rope": false,
+ "model.layers.6.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.6.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.input_layernorm": false,
+ "model.layers.6.post_attention_layernorm": false,
+ "model.layers.7.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.7.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.rope": false,
+ "model.layers.7.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.7.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.input_layernorm": false,
+ "model.layers.7.post_attention_layernorm": false,
+ "model.layers.8.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.rope": false,
+ "model.layers.8.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.input_layernorm": false,
+ "model.layers.8.post_attention_layernorm": false,
+ "model.layers.9.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.rope": false,
+ "model.layers.9.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.input_layernorm": false,
+ "model.layers.9.post_attention_layernorm": false,
+ "model.layers.10.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.10.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.rope": false,
+ "model.layers.10.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.10.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.input_layernorm": false,
+ "model.layers.10.post_attention_layernorm": false,
+ "model.layers.11.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.rope": false,
+ "model.layers.11.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.input_layernorm": false,
+ "model.layers.11.post_attention_layernorm": false,
+ "model.layers.12.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.rope": false,
+ "model.layers.12.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.input_layernorm": false,
+ "model.layers.12.post_attention_layernorm": false,
+ "model.layers.13.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.13.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.rope": false,
+ "model.layers.13.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.13.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.input_layernorm": false,
+ "model.layers.13.post_attention_layernorm": false,
+ "model.layers.14.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.rope": false,
+ "model.layers.14.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.input_layernorm": false,
+ "model.layers.14.post_attention_layernorm": false,
+ "model.layers.15.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.rope": false,
+ "model.layers.15.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.input_layernorm": false,
+ "model.layers.15.post_attention_layernorm": false,
+ "model.layers.16.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.16.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.rope": false,
+ "model.layers.16.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.16.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.input_layernorm": false,
+ "model.layers.16.post_attention_layernorm": false,
+ "model.layers.17.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.rope": false,
+ "model.layers.17.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.input_layernorm": false,
+ "model.layers.17.post_attention_layernorm": false,
+ "model.layers.18.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.rope": false,
+ "model.layers.18.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.input_layernorm": false,
+ "model.layers.18.post_attention_layernorm": false,
+ "model.layers.19.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.19.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.rope": false,
+ "model.layers.19.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.19.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.input_layernorm": false,
+ "model.layers.19.post_attention_layernorm": false,
+ "model.layers.20.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.rope": false,
+ "model.layers.20.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.input_layernorm": false,
+ "model.layers.20.post_attention_layernorm": false,
+ "model.layers.21.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.rope": false,
+ "model.layers.21.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.input_layernorm": false,
+ "model.layers.21.post_attention_layernorm": false,
+ "model.layers.22.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.22.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.rope": false,
+ "model.layers.22.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.22.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.input_layernorm": false,
+ "model.layers.22.post_attention_layernorm": false,
+ "model.layers.23.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.rope": false,
+ "model.layers.23.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.input_layernorm": false,
+ "model.layers.23.post_attention_layernorm": false,
+ "model.layers.24.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.rope": false,
+ "model.layers.24.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.input_layernorm": false,
+ "model.layers.24.post_attention_layernorm": false,
+ "model.layers.25.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.25.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.rope": false,
+ "model.layers.25.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.25.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.input_layernorm": false,
+ "model.layers.25.post_attention_layernorm": false,
+ "model.layers.26.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.rope": false,
+ "model.layers.26.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.input_layernorm": false,
+ "model.layers.26.post_attention_layernorm": false,
+ "model.layers.27.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.rope": false,
+ "model.layers.27.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.input_layernorm": false,
+ "model.layers.27.post_attention_layernorm": false,
+ "model.layers.28.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.28.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.rope": false,
+ "model.layers.28.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.28.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.input_layernorm": false,
+ "model.layers.28.post_attention_layernorm": false,
+ "model.layers.29.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.rope": false,
+ "model.layers.29.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.input_layernorm": false,
+ "model.layers.29.post_attention_layernorm": false,
+ "model.layers.30.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.rope": false,
+ "model.layers.30.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.input_layernorm": false,
+ "model.layers.30.post_attention_layernorm": false,
+ "model.layers.31.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.31.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.rope": false,
+ "model.layers.31.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.31.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.input_layernorm": false,
+ "model.layers.31.post_attention_layernorm": false,
+ "model.layers.32.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.rope": false,
+ "model.layers.32.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.input_layernorm": false,
+ "model.layers.32.post_attention_layernorm": false,
+ "model.layers.33.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.rope": false,
+ "model.layers.33.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.input_layernorm": false,
+ "model.layers.33.post_attention_layernorm": false,
+ "model.layers.34.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.34.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.rope": false,
+ "model.layers.34.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.34.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.input_layernorm": false,
+ "model.layers.34.post_attention_layernorm": false,
+ "model.layers.35.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.rope": false,
+ "model.layers.35.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.input_layernorm": false,
+ "model.layers.35.post_attention_layernorm": false,
+ "model.layers.36.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.rope": false,
+ "model.layers.36.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.input_layernorm": false,
+ "model.layers.36.post_attention_layernorm": false,
+ "model.layers.37.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.37.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.rope": false,
+ "model.layers.37.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.37.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.input_layernorm": false,
+ "model.layers.37.post_attention_layernorm": false,
+ "model.layers.38.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.rope": false,
+ "model.layers.38.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.input_layernorm": false,
+ "model.layers.38.post_attention_layernorm": false,
+ "model.layers.39.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.rope": false,
+ "model.layers.39.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.input_layernorm": false,
+ "model.layers.39.post_attention_layernorm": false,
+ "model.layers.40.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.40.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.rope": false,
+ "model.layers.40.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.40.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.input_layernorm": false,
+ "model.layers.40.post_attention_layernorm": false,
+ "model.layers.41.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.rope": false,
+ "model.layers.41.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.input_layernorm": false,
+ "model.layers.41.post_attention_layernorm": false,
+ "model.layers.42.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.rope": false,
+ "model.layers.42.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.input_layernorm": false,
+ "model.layers.42.post_attention_layernorm": false,
+ "model.layers.43.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.43.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.rope": false,
+ "model.layers.43.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.43.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.input_layernorm": false,
+ "model.layers.43.post_attention_layernorm": false,
+ "model.layers.44.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.rope": false,
+ "model.layers.44.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.input_layernorm": false,
+ "model.layers.44.post_attention_layernorm": false,
+ "model.layers.45.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.rope": false,
+ "model.layers.45.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.input_layernorm": false,
+ "model.layers.45.post_attention_layernorm": false,
+ "model.layers.46.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.46.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.rope": false,
+ "model.layers.46.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.46.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.input_layernorm": false,
+ "model.layers.46.post_attention_layernorm": false,
+ "model.layers.47.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.rope": false,
+ "model.layers.47.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.input_layernorm": false,
+ "model.layers.47.post_attention_layernorm": false,
+ "model.layers.48.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.48.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.48.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.48.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.48.self_attn.rope": false,
+ "model.layers.48.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.48.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.48.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.48.input_layernorm": false,
+ "model.layers.48.post_attention_layernorm": false,
+ "model.layers.49.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.49.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.self_attn.rope": false,
+ "model.layers.49.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.49.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.input_layernorm": false,
+ "model.layers.49.post_attention_layernorm": false,
+ "model.layers.50.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.50.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.50.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.50.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.50.self_attn.rope": false,
+ "model.layers.50.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.50.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.50.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.50.input_layernorm": false,
+ "model.layers.50.post_attention_layernorm": false,
+ "model.layers.51.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.51.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.51.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.51.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.51.self_attn.rope": false,
+ "model.layers.51.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.51.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.51.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.51.input_layernorm": false,
+ "model.layers.51.post_attention_layernorm": false,
+ "model.layers.52.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.52.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.self_attn.rope": false,
+ "model.layers.52.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.52.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.input_layernorm": false,
+ "model.layers.52.post_attention_layernorm": false,
+ "model.layers.53.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.53.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.53.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.53.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.53.self_attn.rope": false,
+ "model.layers.53.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.53.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.53.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.53.input_layernorm": false,
+ "model.layers.53.post_attention_layernorm": false,
+ "model.layers.54.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.54.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.54.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.54.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.54.self_attn.rope": false,
+ "model.layers.54.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.54.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.54.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.54.input_layernorm": false,
+ "model.layers.54.post_attention_layernorm": false,
+ "model.layers.55.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.55.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.self_attn.rope": false,
+ "model.layers.55.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.55.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.input_layernorm": false,
+ "model.layers.55.post_attention_layernorm": false,
+ "model.layers.56.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.56.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.self_attn.rope": false,
+ "model.layers.56.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.56.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.input_layernorm": false,
+ "model.layers.56.post_attention_layernorm": false,
+ "model.layers.57.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.57.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.self_attn.rope": false,
+ "model.layers.57.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.57.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.input_layernorm": false,
+ "model.layers.57.post_attention_layernorm": false,
+ "model.layers.58.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.58.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.self_attn.rope": false,
+ "model.layers.58.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.58.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.input_layernorm": false,
+ "model.layers.58.post_attention_layernorm": false,
+ "model.layers.59.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.59.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.self_attn.rope": false,
+ "model.layers.59.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.59.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.input_layernorm": false,
+ "model.layers.59.post_attention_layernorm": false,
+ "model.layers.60.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.60.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.self_attn.rope": false,
+ "model.layers.60.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.60.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.input_layernorm": false,
+ "model.layers.60.post_attention_layernorm": false,
+ "model.layers.61.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.61.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.self_attn.rope": false,
+ "model.layers.61.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.61.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.input_layernorm": false,
+ "model.layers.61.post_attention_layernorm": false,
+ "model.layers.62.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.62.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.self_attn.rope": false,
+ "model.layers.62.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.62.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.input_layernorm": false,
+ "model.layers.62.post_attention_layernorm": false,
+ "model.layers.63.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.63.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.self_attn.rope": false,
+ "model.layers.63.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.63.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.input_layernorm": false,
+ "model.layers.63.post_attention_layernorm": false,
+ "model.norm": false,
+ "lm_head": {
+ "group_size": 64,
+ "bits": 6
+ }
+ },
+ "quantization_config": {
+ "group_size": 64,
+ "bits": null,
+ "model.embed_tokens": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.0.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.rope": false,
+ "model.layers.0.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.0.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.input_layernorm": false,
+ "model.layers.0.post_attention_layernorm": false,
+ "model.layers.1.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.1.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.rope": false,
+ "model.layers.1.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.1.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.input_layernorm": false,
+ "model.layers.1.post_attention_layernorm": false,
+ "model.layers.2.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.2.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.rope": false,
+ "model.layers.2.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.2.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.input_layernorm": false,
+ "model.layers.2.post_attention_layernorm": false,
+ "model.layers.3.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.3.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.rope": false,
+ "model.layers.3.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.3.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.input_layernorm": false,
+ "model.layers.3.post_attention_layernorm": false,
+ "model.layers.4.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.4.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.rope": false,
+ "model.layers.4.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.4.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.input_layernorm": false,
+ "model.layers.4.post_attention_layernorm": false,
+ "model.layers.5.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.5.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.rope": false,
+ "model.layers.5.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.5.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.input_layernorm": false,
+ "model.layers.5.post_attention_layernorm": false,
+ "model.layers.6.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.6.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.rope": false,
+ "model.layers.6.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.6.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.input_layernorm": false,
+ "model.layers.6.post_attention_layernorm": false,
+ "model.layers.7.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.7.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.rope": false,
+ "model.layers.7.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.7.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.input_layernorm": false,
+ "model.layers.7.post_attention_layernorm": false,
+ "model.layers.8.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.rope": false,
+ "model.layers.8.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.input_layernorm": false,
+ "model.layers.8.post_attention_layernorm": false,
+ "model.layers.9.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.rope": false,
+ "model.layers.9.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.input_layernorm": false,
+ "model.layers.9.post_attention_layernorm": false,
+ "model.layers.10.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.10.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.rope": false,
+ "model.layers.10.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.10.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.input_layernorm": false,
+ "model.layers.10.post_attention_layernorm": false,
+ "model.layers.11.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.rope": false,
+ "model.layers.11.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.input_layernorm": false,
+ "model.layers.11.post_attention_layernorm": false,
+ "model.layers.12.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.rope": false,
+ "model.layers.12.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.input_layernorm": false,
+ "model.layers.12.post_attention_layernorm": false,
+ "model.layers.13.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.13.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.rope": false,
+ "model.layers.13.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.13.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.input_layernorm": false,
+ "model.layers.13.post_attention_layernorm": false,
+ "model.layers.14.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.rope": false,
+ "model.layers.14.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.input_layernorm": false,
+ "model.layers.14.post_attention_layernorm": false,
+ "model.layers.15.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.rope": false,
+ "model.layers.15.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.input_layernorm": false,
+ "model.layers.15.post_attention_layernorm": false,
+ "model.layers.16.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.16.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.rope": false,
+ "model.layers.16.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.16.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.input_layernorm": false,
+ "model.layers.16.post_attention_layernorm": false,
+ "model.layers.17.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.rope": false,
+ "model.layers.17.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.input_layernorm": false,
+ "model.layers.17.post_attention_layernorm": false,
+ "model.layers.18.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.rope": false,
+ "model.layers.18.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.input_layernorm": false,
+ "model.layers.18.post_attention_layernorm": false,
+ "model.layers.19.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.19.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.rope": false,
+ "model.layers.19.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.19.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.input_layernorm": false,
+ "model.layers.19.post_attention_layernorm": false,
+ "model.layers.20.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.rope": false,
+ "model.layers.20.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.input_layernorm": false,
+ "model.layers.20.post_attention_layernorm": false,
+ "model.layers.21.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.rope": false,
+ "model.layers.21.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.input_layernorm": false,
+ "model.layers.21.post_attention_layernorm": false,
+ "model.layers.22.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.22.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.rope": false,
+ "model.layers.22.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.22.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.input_layernorm": false,
+ "model.layers.22.post_attention_layernorm": false,
+ "model.layers.23.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.rope": false,
+ "model.layers.23.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.input_layernorm": false,
+ "model.layers.23.post_attention_layernorm": false,
+ "model.layers.24.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.rope": false,
+ "model.layers.24.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.input_layernorm": false,
+ "model.layers.24.post_attention_layernorm": false,
+ "model.layers.25.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.25.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.rope": false,
+ "model.layers.25.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.25.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.input_layernorm": false,
+ "model.layers.25.post_attention_layernorm": false,
+ "model.layers.26.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.rope": false,
+ "model.layers.26.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.input_layernorm": false,
+ "model.layers.26.post_attention_layernorm": false,
+ "model.layers.27.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.rope": false,
+ "model.layers.27.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.input_layernorm": false,
+ "model.layers.27.post_attention_layernorm": false,
+ "model.layers.28.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.28.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.rope": false,
+ "model.layers.28.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.28.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.input_layernorm": false,
+ "model.layers.28.post_attention_layernorm": false,
+ "model.layers.29.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.rope": false,
+ "model.layers.29.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.input_layernorm": false,
+ "model.layers.29.post_attention_layernorm": false,
+ "model.layers.30.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.rope": false,
+ "model.layers.30.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.input_layernorm": false,
+ "model.layers.30.post_attention_layernorm": false,
+ "model.layers.31.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.31.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.rope": false,
+ "model.layers.31.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.31.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.input_layernorm": false,
+ "model.layers.31.post_attention_layernorm": false,
+ "model.layers.32.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.rope": false,
+ "model.layers.32.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.input_layernorm": false,
+ "model.layers.32.post_attention_layernorm": false,
+ "model.layers.33.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.rope": false,
+ "model.layers.33.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.input_layernorm": false,
+ "model.layers.33.post_attention_layernorm": false,
+ "model.layers.34.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.34.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.rope": false,
+ "model.layers.34.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.34.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.input_layernorm": false,
+ "model.layers.34.post_attention_layernorm": false,
+ "model.layers.35.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.rope": false,
+ "model.layers.35.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.input_layernorm": false,
+ "model.layers.35.post_attention_layernorm": false,
+ "model.layers.36.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.rope": false,
+ "model.layers.36.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.input_layernorm": false,
+ "model.layers.36.post_attention_layernorm": false,
+ "model.layers.37.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.37.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.rope": false,
+ "model.layers.37.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.37.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.input_layernorm": false,
+ "model.layers.37.post_attention_layernorm": false,
+ "model.layers.38.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.rope": false,
+ "model.layers.38.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.input_layernorm": false,
+ "model.layers.38.post_attention_layernorm": false,
+ "model.layers.39.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.rope": false,
+ "model.layers.39.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.input_layernorm": false,
+ "model.layers.39.post_attention_layernorm": false,
+ "model.layers.40.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.40.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.rope": false,
+ "model.layers.40.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.40.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.input_layernorm": false,
+ "model.layers.40.post_attention_layernorm": false,
+ "model.layers.41.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.rope": false,
+ "model.layers.41.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.input_layernorm": false,
+ "model.layers.41.post_attention_layernorm": false,
+ "model.layers.42.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.rope": false,
+ "model.layers.42.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.input_layernorm": false,
+ "model.layers.42.post_attention_layernorm": false,
+ "model.layers.43.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.43.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.rope": false,
+ "model.layers.43.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.43.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.input_layernorm": false,
+ "model.layers.43.post_attention_layernorm": false,
+ "model.layers.44.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.rope": false,
+ "model.layers.44.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.input_layernorm": false,
+ "model.layers.44.post_attention_layernorm": false,
+ "model.layers.45.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.rope": false,
+ "model.layers.45.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.input_layernorm": false,
+ "model.layers.45.post_attention_layernorm": false,
+ "model.layers.46.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.46.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.rope": false,
+ "model.layers.46.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.46.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.input_layernorm": false,
+ "model.layers.46.post_attention_layernorm": false,
+ "model.layers.47.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.rope": false,
+ "model.layers.47.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.input_layernorm": false,
+ "model.layers.47.post_attention_layernorm": false,
+ "model.layers.48.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.48.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.48.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.48.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.48.self_attn.rope": false,
+ "model.layers.48.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.48.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.48.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.48.input_layernorm": false,
+ "model.layers.48.post_attention_layernorm": false,
+ "model.layers.49.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.49.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.self_attn.rope": false,
+ "model.layers.49.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.49.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.input_layernorm": false,
+ "model.layers.49.post_attention_layernorm": false,
+ "model.layers.50.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.50.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.50.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.50.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.50.self_attn.rope": false,
+ "model.layers.50.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.50.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.50.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.50.input_layernorm": false,
+ "model.layers.50.post_attention_layernorm": false,
+ "model.layers.51.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.51.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.51.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.51.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.51.self_attn.rope": false,
+ "model.layers.51.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.51.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.51.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.51.input_layernorm": false,
+ "model.layers.51.post_attention_layernorm": false,
+ "model.layers.52.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.52.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.self_attn.rope": false,
+ "model.layers.52.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.52.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.input_layernorm": false,
+ "model.layers.52.post_attention_layernorm": false,
+ "model.layers.53.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.53.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.53.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.53.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.53.self_attn.rope": false,
+ "model.layers.53.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.53.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.53.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.53.input_layernorm": false,
+ "model.layers.53.post_attention_layernorm": false,
+ "model.layers.54.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.54.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.54.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.54.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.54.self_attn.rope": false,
+ "model.layers.54.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.54.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.54.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.54.input_layernorm": false,
+ "model.layers.54.post_attention_layernorm": false,
+ "model.layers.55.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.55.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.self_attn.rope": false,
+ "model.layers.55.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.55.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.input_layernorm": false,
+ "model.layers.55.post_attention_layernorm": false,
+ "model.layers.56.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.56.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.self_attn.rope": false,
+ "model.layers.56.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.56.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.input_layernorm": false,
+ "model.layers.56.post_attention_layernorm": false,
+ "model.layers.57.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.57.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.self_attn.rope": false,
+ "model.layers.57.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.57.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.input_layernorm": false,
+ "model.layers.57.post_attention_layernorm": false,
+ "model.layers.58.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.58.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.self_attn.rope": false,
+ "model.layers.58.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.58.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.input_layernorm": false,
+ "model.layers.58.post_attention_layernorm": false,
+ "model.layers.59.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.59.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.self_attn.rope": false,
+ "model.layers.59.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.59.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.input_layernorm": false,
+ "model.layers.59.post_attention_layernorm": false,
+ "model.layers.60.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.60.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.self_attn.rope": false,
+ "model.layers.60.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.60.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.input_layernorm": false,
+ "model.layers.60.post_attention_layernorm": false,
+ "model.layers.61.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.61.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.self_attn.rope": false,
+ "model.layers.61.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.61.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.input_layernorm": false,
+ "model.layers.61.post_attention_layernorm": false,
+ "model.layers.62.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.62.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.self_attn.rope": false,
+ "model.layers.62.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.62.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.input_layernorm": false,
+ "model.layers.62.post_attention_layernorm": false,
+ "model.layers.63.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.63.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.self_attn.rope": false,
+ "model.layers.63.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "model.layers.63.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.input_layernorm": false,
+ "model.layers.63.post_attention_layernorm": false,
+ "model.norm": false,
+ "lm_head": {
+ "group_size": 64,
+ "bits": 6
+ }
+ },
+ "rms_norm_eps": 1e-05,
+ "rope_theta": 1000000.0,
+ "sliding_window": 131072,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.43.1",
+ "use_cache": true,
+ "use_sliding_window": false,
+ "vocab_size": 152064
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00001-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00001-of-00004.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..245f8e0ab514d53d02560168c60f972cf98b5943
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00001-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:429cf44b2e5598d801cfa4fddaae42efcb4548ba46d9e9bf7c2e26096fb16675
+size 5310183468
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00002-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00002-of-00004.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..eaf22c913e4bcfc97a0071f5c25845e0e27a65aa
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00002-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d596a31fd03bc688c548db84b801254461a09aa55250242f20d1cfed4d1a5ce
+size 5367127243
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00003-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00003-of-00004.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..bcfe8569333066582eb8be5bd48e0c3410da0931
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00003-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07807bb0bf699e10be76a4a1d2b30ff0783ccc63088618f8c5362bee39c1433d
+size 5337609940
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00004-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00004-of-00004.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fb97da7d96d0fc7f1cd1f9b7e237b618cac88569
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00004-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88f1c10d332dc8dc43acd62a8c54803283e672b671829d4f7820a10e0a1ed038
+size 3785604672
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..3f18e4cd2a8488054f4c863faf851c0c45b04880
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model.safetensors.index.json
@@ -0,0 +1,1678 @@
+{
+ "metadata": {
+ "total_size": 19800336384
+ },
+ "weight_map": {
+ "lm_head.biases": "model-00004-of-00004.safetensors",
+ "lm_head.scales": "model-00004-of-00004.safetensors",
+ "lm_head.weight": "model-00004-of-00004.safetensors",
+ "model.embed_tokens.biases": "model-00001-of-00004.safetensors",
+ "model.embed_tokens.scales": "model-00001-of-00004.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.12.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.12.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.13.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.13.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.13.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.13.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.14.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.14.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.14.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.14.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.15.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.15.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.15.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.15.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.15.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.16.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.16.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.16.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.16.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.16.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.17.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.17.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.17.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.17.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.17.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.17.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.27.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.27.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.28.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.28.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.28.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.28.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.28.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.29.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.29.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.29.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.29.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.29.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.30.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.30.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.30.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.30.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.30.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.31.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.31.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.31.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.31.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.31.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.32.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.32.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.32.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.32.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.32.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.33.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.33.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.33.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.33.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.33.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.34.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.34.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.34.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.34.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.34.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.34.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.35.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.35.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.35.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.35.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.35.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.35.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.35.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.35.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.35.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.36.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.36.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.36.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.36.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.36.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.36.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.36.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.36.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.36.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.37.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.37.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.37.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.37.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.37.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.40.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.41.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.41.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.41.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.41.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.41.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.41.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.42.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.42.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.42.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.42.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.42.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.42.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.42.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.42.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.42.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.42.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.43.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.43.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.43.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.43.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.43.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.43.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.43.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.43.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.43.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.43.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.43.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.44.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.44.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.44.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.44.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.44.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.44.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.44.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.44.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.44.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.44.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.44.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.45.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.45.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.45.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.45.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.45.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.45.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.45.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.45.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.45.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.45.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.46.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.46.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.46.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.46.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.46.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.46.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.46.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.46.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.46.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.46.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.47.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.47.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.47.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.47.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.47.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.47.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.47.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.47.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.47.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.47.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.48.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.48.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.48.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.48.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.48.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.48.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.48.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.48.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.48.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.48.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.48.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.49.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.49.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.49.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.49.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.49.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.49.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.49.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.49.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.49.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.49.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.49.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.50.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.50.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.50.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.50.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.50.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.50.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.50.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.50.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.50.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.50.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.50.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.51.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.51.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.51.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.51.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.51.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.51.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.51.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.51.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.51.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.51.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.51.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.52.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.52.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.52.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.52.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.52.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.52.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.52.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.52.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.52.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.52.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.52.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.53.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.53.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.53.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.53.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.53.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.53.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.53.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.53.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.53.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.53.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.53.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.53.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.54.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.54.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.54.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.54.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.54.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.54.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.54.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.54.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.54.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.54.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.54.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.55.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.55.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.55.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.55.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.55.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.55.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.55.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.55.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.55.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.55.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.55.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.56.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.56.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.56.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.56.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.56.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.56.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.56.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.56.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.56.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.56.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.56.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.57.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.57.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.57.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.57.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.57.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.57.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.57.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.57.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.57.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.57.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.57.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.58.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.58.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.58.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.58.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.58.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.58.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.58.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.58.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.58.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.58.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.58.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.59.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.59.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.59.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.59.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.59.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.59.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.59.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.59.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.59.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.59.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.59.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.60.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.60.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.60.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.60.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.60.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.60.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.60.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.60.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.60.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.60.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.60.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.61.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.61.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.61.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.61.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.61.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.61.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.61.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.61.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.61.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.61.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.61.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.62.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.62.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.62.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.62.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.62.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.62.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.62.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.62.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.62.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.62.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.62.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.63.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.63.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.63.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.63.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.63.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.63.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.63.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.63.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.63.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.63.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.63.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.norm.weight": "model-00004-of-00004.safetensors"
+ }
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/tokenizer_config.json
@@ -0,0 +1,195 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/config.json b/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ad55fbcc50420194feca55ea5f985a102fa7d648
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/config.json
@@ -0,0 +1,4021 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 5120,
+ "initializer_range": 0.02,
+ "intermediate_size": 27648,
+ "max_position_embeddings": 131072,
+ "max_window_layers": 64,
+ "model_type": "qwen2",
+ "num_attention_heads": 40,
+ "num_hidden_layers": 64,
+ "num_key_value_heads": 8,
+ "quantization": {
+ "group_size": 64,
+ "bits": null,
+ "model.embed_tokens": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.0.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.rope": false,
+ "model.layers.0.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.0.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.input_layernorm": false,
+ "model.layers.0.post_attention_layernorm": false,
+ "model.layers.1.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.1.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.rope": false,
+ "model.layers.1.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.1.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.input_layernorm": false,
+ "model.layers.1.post_attention_layernorm": false,
+ "model.layers.2.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.2.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.rope": false,
+ "model.layers.2.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.2.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.input_layernorm": false,
+ "model.layers.2.post_attention_layernorm": false,
+ "model.layers.3.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.3.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.rope": false,
+ "model.layers.3.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.3.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.input_layernorm": false,
+ "model.layers.3.post_attention_layernorm": false,
+ "model.layers.4.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.4.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.rope": false,
+ "model.layers.4.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.4.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.input_layernorm": false,
+ "model.layers.4.post_attention_layernorm": false,
+ "model.layers.5.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.5.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.rope": false,
+ "model.layers.5.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.5.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.input_layernorm": false,
+ "model.layers.5.post_attention_layernorm": false,
+ "model.layers.6.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.6.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.rope": false,
+ "model.layers.6.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.6.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.input_layernorm": false,
+ "model.layers.6.post_attention_layernorm": false,
+ "model.layers.7.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.7.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.rope": false,
+ "model.layers.7.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.7.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.input_layernorm": false,
+ "model.layers.7.post_attention_layernorm": false,
+ "model.layers.8.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.rope": false,
+ "model.layers.8.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.input_layernorm": false,
+ "model.layers.8.post_attention_layernorm": false,
+ "model.layers.9.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.rope": false,
+ "model.layers.9.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.input_layernorm": false,
+ "model.layers.9.post_attention_layernorm": false,
+ "model.layers.10.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.10.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.rope": false,
+ "model.layers.10.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.10.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.input_layernorm": false,
+ "model.layers.10.post_attention_layernorm": false,
+ "model.layers.11.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.rope": false,
+ "model.layers.11.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.input_layernorm": false,
+ "model.layers.11.post_attention_layernorm": false,
+ "model.layers.12.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.rope": false,
+ "model.layers.12.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.input_layernorm": false,
+ "model.layers.12.post_attention_layernorm": false,
+ "model.layers.13.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.13.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.rope": false,
+ "model.layers.13.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.13.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.input_layernorm": false,
+ "model.layers.13.post_attention_layernorm": false,
+ "model.layers.14.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.rope": false,
+ "model.layers.14.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.input_layernorm": false,
+ "model.layers.14.post_attention_layernorm": false,
+ "model.layers.15.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.rope": false,
+ "model.layers.15.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.input_layernorm": false,
+ "model.layers.15.post_attention_layernorm": false,
+ "model.layers.16.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.16.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.rope": false,
+ "model.layers.16.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.16.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.input_layernorm": false,
+ "model.layers.16.post_attention_layernorm": false,
+ "model.layers.17.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.rope": false,
+ "model.layers.17.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.input_layernorm": false,
+ "model.layers.17.post_attention_layernorm": false,
+ "model.layers.18.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.rope": false,
+ "model.layers.18.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.input_layernorm": false,
+ "model.layers.18.post_attention_layernorm": false,
+ "model.layers.19.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.19.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.rope": false,
+ "model.layers.19.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.19.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.input_layernorm": false,
+ "model.layers.19.post_attention_layernorm": false,
+ "model.layers.20.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.rope": false,
+ "model.layers.20.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.input_layernorm": false,
+ "model.layers.20.post_attention_layernorm": false,
+ "model.layers.21.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.rope": false,
+ "model.layers.21.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.input_layernorm": false,
+ "model.layers.21.post_attention_layernorm": false,
+ "model.layers.22.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.22.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.rope": false,
+ "model.layers.22.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.22.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.input_layernorm": false,
+ "model.layers.22.post_attention_layernorm": false,
+ "model.layers.23.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.rope": false,
+ "model.layers.23.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.input_layernorm": false,
+ "model.layers.23.post_attention_layernorm": false,
+ "model.layers.24.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.rope": false,
+ "model.layers.24.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.input_layernorm": false,
+ "model.layers.24.post_attention_layernorm": false,
+ "model.layers.25.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.25.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.rope": false,
+ "model.layers.25.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.25.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.input_layernorm": false,
+ "model.layers.25.post_attention_layernorm": false,
+ "model.layers.26.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.rope": false,
+ "model.layers.26.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.input_layernorm": false,
+ "model.layers.26.post_attention_layernorm": false,
+ "model.layers.27.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.rope": false,
+ "model.layers.27.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.input_layernorm": false,
+ "model.layers.27.post_attention_layernorm": false,
+ "model.layers.28.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.28.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.rope": false,
+ "model.layers.28.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.28.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.input_layernorm": false,
+ "model.layers.28.post_attention_layernorm": false,
+ "model.layers.29.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.rope": false,
+ "model.layers.29.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.input_layernorm": false,
+ "model.layers.29.post_attention_layernorm": false,
+ "model.layers.30.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.rope": false,
+ "model.layers.30.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.input_layernorm": false,
+ "model.layers.30.post_attention_layernorm": false,
+ "model.layers.31.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.31.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.rope": false,
+ "model.layers.31.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.31.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.input_layernorm": false,
+ "model.layers.31.post_attention_layernorm": false,
+ "model.layers.32.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.rope": false,
+ "model.layers.32.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.input_layernorm": false,
+ "model.layers.32.post_attention_layernorm": false,
+ "model.layers.33.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.rope": false,
+ "model.layers.33.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.input_layernorm": false,
+ "model.layers.33.post_attention_layernorm": false,
+ "model.layers.34.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.34.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.rope": false,
+ "model.layers.34.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.34.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.input_layernorm": false,
+ "model.layers.34.post_attention_layernorm": false,
+ "model.layers.35.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.rope": false,
+ "model.layers.35.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.input_layernorm": false,
+ "model.layers.35.post_attention_layernorm": false,
+ "model.layers.36.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.rope": false,
+ "model.layers.36.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.input_layernorm": false,
+ "model.layers.36.post_attention_layernorm": false,
+ "model.layers.37.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.37.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.rope": false,
+ "model.layers.37.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.37.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.input_layernorm": false,
+ "model.layers.37.post_attention_layernorm": false,
+ "model.layers.38.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.rope": false,
+ "model.layers.38.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.input_layernorm": false,
+ "model.layers.38.post_attention_layernorm": false,
+ "model.layers.39.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.rope": false,
+ "model.layers.39.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.input_layernorm": false,
+ "model.layers.39.post_attention_layernorm": false,
+ "model.layers.40.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.40.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.rope": false,
+ "model.layers.40.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.40.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.input_layernorm": false,
+ "model.layers.40.post_attention_layernorm": false,
+ "model.layers.41.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.rope": false,
+ "model.layers.41.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.input_layernorm": false,
+ "model.layers.41.post_attention_layernorm": false,
+ "model.layers.42.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.rope": false,
+ "model.layers.42.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.input_layernorm": false,
+ "model.layers.42.post_attention_layernorm": false,
+ "model.layers.43.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.43.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.rope": false,
+ "model.layers.43.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.43.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.input_layernorm": false,
+ "model.layers.43.post_attention_layernorm": false,
+ "model.layers.44.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.rope": false,
+ "model.layers.44.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.input_layernorm": false,
+ "model.layers.44.post_attention_layernorm": false,
+ "model.layers.45.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.rope": false,
+ "model.layers.45.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.input_layernorm": false,
+ "model.layers.45.post_attention_layernorm": false,
+ "model.layers.46.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.46.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.rope": false,
+ "model.layers.46.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.46.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.input_layernorm": false,
+ "model.layers.46.post_attention_layernorm": false,
+ "model.layers.47.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.rope": false,
+ "model.layers.47.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.input_layernorm": false,
+ "model.layers.47.post_attention_layernorm": false,
+ "model.layers.48.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.48.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.48.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.48.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.48.self_attn.rope": false,
+ "model.layers.48.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.48.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.48.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.48.input_layernorm": false,
+ "model.layers.48.post_attention_layernorm": false,
+ "model.layers.49.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.49.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.self_attn.rope": false,
+ "model.layers.49.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.49.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.input_layernorm": false,
+ "model.layers.49.post_attention_layernorm": false,
+ "model.layers.50.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.50.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.50.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.50.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.50.self_attn.rope": false,
+ "model.layers.50.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.50.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.50.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.50.input_layernorm": false,
+ "model.layers.50.post_attention_layernorm": false,
+ "model.layers.51.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.51.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.51.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.51.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.51.self_attn.rope": false,
+ "model.layers.51.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.51.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.51.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.51.input_layernorm": false,
+ "model.layers.51.post_attention_layernorm": false,
+ "model.layers.52.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.52.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.self_attn.rope": false,
+ "model.layers.52.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.52.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.input_layernorm": false,
+ "model.layers.52.post_attention_layernorm": false,
+ "model.layers.53.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.53.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.53.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.53.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.53.self_attn.rope": false,
+ "model.layers.53.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.53.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.53.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.53.input_layernorm": false,
+ "model.layers.53.post_attention_layernorm": false,
+ "model.layers.54.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.54.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.54.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.54.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.54.self_attn.rope": false,
+ "model.layers.54.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.54.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.54.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.54.input_layernorm": false,
+ "model.layers.54.post_attention_layernorm": false,
+ "model.layers.55.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.55.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.self_attn.rope": false,
+ "model.layers.55.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.55.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.input_layernorm": false,
+ "model.layers.55.post_attention_layernorm": false,
+ "model.layers.56.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.56.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.self_attn.rope": false,
+ "model.layers.56.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.56.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.input_layernorm": false,
+ "model.layers.56.post_attention_layernorm": false,
+ "model.layers.57.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.57.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.self_attn.rope": false,
+ "model.layers.57.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.57.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.input_layernorm": false,
+ "model.layers.57.post_attention_layernorm": false,
+ "model.layers.58.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.58.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.self_attn.rope": false,
+ "model.layers.58.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.58.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.input_layernorm": false,
+ "model.layers.58.post_attention_layernorm": false,
+ "model.layers.59.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.59.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.self_attn.rope": false,
+ "model.layers.59.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.59.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.input_layernorm": false,
+ "model.layers.59.post_attention_layernorm": false,
+ "model.layers.60.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.60.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.self_attn.rope": false,
+ "model.layers.60.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.60.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.input_layernorm": false,
+ "model.layers.60.post_attention_layernorm": false,
+ "model.layers.61.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.61.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.self_attn.rope": false,
+ "model.layers.61.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.61.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.input_layernorm": false,
+ "model.layers.61.post_attention_layernorm": false,
+ "model.layers.62.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.62.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.self_attn.rope": false,
+ "model.layers.62.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.62.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.input_layernorm": false,
+ "model.layers.62.post_attention_layernorm": false,
+ "model.layers.63.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.63.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.self_attn.rope": false,
+ "model.layers.63.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.63.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.input_layernorm": false,
+ "model.layers.63.post_attention_layernorm": false,
+ "model.norm": false,
+ "lm_head": {
+ "group_size": 64,
+ "bits": 8
+ }
+ },
+ "quantization_config": {
+ "group_size": 64,
+ "bits": null,
+ "model.embed_tokens": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.0.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.self_attn.rope": false,
+ "model.layers.0.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.0.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.0.input_layernorm": false,
+ "model.layers.0.post_attention_layernorm": false,
+ "model.layers.1.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.1.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.self_attn.rope": false,
+ "model.layers.1.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.1.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.1.input_layernorm": false,
+ "model.layers.1.post_attention_layernorm": false,
+ "model.layers.2.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.2.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.self_attn.rope": false,
+ "model.layers.2.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.2.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.2.input_layernorm": false,
+ "model.layers.2.post_attention_layernorm": false,
+ "model.layers.3.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.3.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.self_attn.rope": false,
+ "model.layers.3.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.3.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.3.input_layernorm": false,
+ "model.layers.3.post_attention_layernorm": false,
+ "model.layers.4.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.4.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.self_attn.rope": false,
+ "model.layers.4.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.4.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.4.input_layernorm": false,
+ "model.layers.4.post_attention_layernorm": false,
+ "model.layers.5.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.5.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.self_attn.rope": false,
+ "model.layers.5.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.5.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.5.input_layernorm": false,
+ "model.layers.5.post_attention_layernorm": false,
+ "model.layers.6.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.6.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.self_attn.rope": false,
+ "model.layers.6.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.6.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.6.input_layernorm": false,
+ "model.layers.6.post_attention_layernorm": false,
+ "model.layers.7.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.7.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.self_attn.rope": false,
+ "model.layers.7.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.7.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.7.input_layernorm": false,
+ "model.layers.7.post_attention_layernorm": false,
+ "model.layers.8.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.self_attn.rope": false,
+ "model.layers.8.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.8.input_layernorm": false,
+ "model.layers.8.post_attention_layernorm": false,
+ "model.layers.9.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.self_attn.rope": false,
+ "model.layers.9.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.9.input_layernorm": false,
+ "model.layers.9.post_attention_layernorm": false,
+ "model.layers.10.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.10.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.self_attn.rope": false,
+ "model.layers.10.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.10.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.10.input_layernorm": false,
+ "model.layers.10.post_attention_layernorm": false,
+ "model.layers.11.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.self_attn.rope": false,
+ "model.layers.11.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.11.input_layernorm": false,
+ "model.layers.11.post_attention_layernorm": false,
+ "model.layers.12.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.self_attn.rope": false,
+ "model.layers.12.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.12.input_layernorm": false,
+ "model.layers.12.post_attention_layernorm": false,
+ "model.layers.13.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.13.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.self_attn.rope": false,
+ "model.layers.13.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.13.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.13.input_layernorm": false,
+ "model.layers.13.post_attention_layernorm": false,
+ "model.layers.14.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.self_attn.rope": false,
+ "model.layers.14.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.14.input_layernorm": false,
+ "model.layers.14.post_attention_layernorm": false,
+ "model.layers.15.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.self_attn.rope": false,
+ "model.layers.15.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.15.input_layernorm": false,
+ "model.layers.15.post_attention_layernorm": false,
+ "model.layers.16.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.16.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.self_attn.rope": false,
+ "model.layers.16.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.16.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.16.input_layernorm": false,
+ "model.layers.16.post_attention_layernorm": false,
+ "model.layers.17.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.self_attn.rope": false,
+ "model.layers.17.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.17.input_layernorm": false,
+ "model.layers.17.post_attention_layernorm": false,
+ "model.layers.18.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.self_attn.rope": false,
+ "model.layers.18.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.18.input_layernorm": false,
+ "model.layers.18.post_attention_layernorm": false,
+ "model.layers.19.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.19.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.self_attn.rope": false,
+ "model.layers.19.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.19.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.19.input_layernorm": false,
+ "model.layers.19.post_attention_layernorm": false,
+ "model.layers.20.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.self_attn.rope": false,
+ "model.layers.20.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.20.input_layernorm": false,
+ "model.layers.20.post_attention_layernorm": false,
+ "model.layers.21.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.self_attn.rope": false,
+ "model.layers.21.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.21.input_layernorm": false,
+ "model.layers.21.post_attention_layernorm": false,
+ "model.layers.22.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.22.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.self_attn.rope": false,
+ "model.layers.22.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.22.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.22.input_layernorm": false,
+ "model.layers.22.post_attention_layernorm": false,
+ "model.layers.23.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.self_attn.rope": false,
+ "model.layers.23.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.23.input_layernorm": false,
+ "model.layers.23.post_attention_layernorm": false,
+ "model.layers.24.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.self_attn.rope": false,
+ "model.layers.24.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.24.input_layernorm": false,
+ "model.layers.24.post_attention_layernorm": false,
+ "model.layers.25.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.25.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.self_attn.rope": false,
+ "model.layers.25.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.25.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.25.input_layernorm": false,
+ "model.layers.25.post_attention_layernorm": false,
+ "model.layers.26.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.self_attn.rope": false,
+ "model.layers.26.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.26.input_layernorm": false,
+ "model.layers.26.post_attention_layernorm": false,
+ "model.layers.27.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.self_attn.rope": false,
+ "model.layers.27.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.27.input_layernorm": false,
+ "model.layers.27.post_attention_layernorm": false,
+ "model.layers.28.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.28.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.self_attn.rope": false,
+ "model.layers.28.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.28.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.28.input_layernorm": false,
+ "model.layers.28.post_attention_layernorm": false,
+ "model.layers.29.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.self_attn.rope": false,
+ "model.layers.29.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.29.input_layernorm": false,
+ "model.layers.29.post_attention_layernorm": false,
+ "model.layers.30.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.self_attn.rope": false,
+ "model.layers.30.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.30.input_layernorm": false,
+ "model.layers.30.post_attention_layernorm": false,
+ "model.layers.31.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.31.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.self_attn.rope": false,
+ "model.layers.31.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.31.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.31.input_layernorm": false,
+ "model.layers.31.post_attention_layernorm": false,
+ "model.layers.32.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.self_attn.rope": false,
+ "model.layers.32.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.32.input_layernorm": false,
+ "model.layers.32.post_attention_layernorm": false,
+ "model.layers.33.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.self_attn.rope": false,
+ "model.layers.33.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.33.input_layernorm": false,
+ "model.layers.33.post_attention_layernorm": false,
+ "model.layers.34.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.34.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.self_attn.rope": false,
+ "model.layers.34.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.34.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.34.input_layernorm": false,
+ "model.layers.34.post_attention_layernorm": false,
+ "model.layers.35.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.self_attn.rope": false,
+ "model.layers.35.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.35.input_layernorm": false,
+ "model.layers.35.post_attention_layernorm": false,
+ "model.layers.36.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.self_attn.rope": false,
+ "model.layers.36.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.36.input_layernorm": false,
+ "model.layers.36.post_attention_layernorm": false,
+ "model.layers.37.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.37.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.self_attn.rope": false,
+ "model.layers.37.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.37.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.37.input_layernorm": false,
+ "model.layers.37.post_attention_layernorm": false,
+ "model.layers.38.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.self_attn.rope": false,
+ "model.layers.38.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.38.input_layernorm": false,
+ "model.layers.38.post_attention_layernorm": false,
+ "model.layers.39.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.self_attn.rope": false,
+ "model.layers.39.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.39.input_layernorm": false,
+ "model.layers.39.post_attention_layernorm": false,
+ "model.layers.40.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.40.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.self_attn.rope": false,
+ "model.layers.40.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.40.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.40.input_layernorm": false,
+ "model.layers.40.post_attention_layernorm": false,
+ "model.layers.41.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.self_attn.rope": false,
+ "model.layers.41.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.41.input_layernorm": false,
+ "model.layers.41.post_attention_layernorm": false,
+ "model.layers.42.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.self_attn.rope": false,
+ "model.layers.42.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.42.input_layernorm": false,
+ "model.layers.42.post_attention_layernorm": false,
+ "model.layers.43.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.43.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.self_attn.rope": false,
+ "model.layers.43.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.43.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.43.input_layernorm": false,
+ "model.layers.43.post_attention_layernorm": false,
+ "model.layers.44.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.self_attn.rope": false,
+ "model.layers.44.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.44.input_layernorm": false,
+ "model.layers.44.post_attention_layernorm": false,
+ "model.layers.45.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.self_attn.rope": false,
+ "model.layers.45.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.45.input_layernorm": false,
+ "model.layers.45.post_attention_layernorm": false,
+ "model.layers.46.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.46.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.self_attn.rope": false,
+ "model.layers.46.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.46.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.46.input_layernorm": false,
+ "model.layers.46.post_attention_layernorm": false,
+ "model.layers.47.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.self_attn.rope": false,
+ "model.layers.47.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.47.input_layernorm": false,
+ "model.layers.47.post_attention_layernorm": false,
+ "model.layers.48.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.48.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.48.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.48.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.48.self_attn.rope": false,
+ "model.layers.48.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.48.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.48.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.48.input_layernorm": false,
+ "model.layers.48.post_attention_layernorm": false,
+ "model.layers.49.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.49.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.self_attn.rope": false,
+ "model.layers.49.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.49.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.49.input_layernorm": false,
+ "model.layers.49.post_attention_layernorm": false,
+ "model.layers.50.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.50.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.50.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.50.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.50.self_attn.rope": false,
+ "model.layers.50.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.50.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.50.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.50.input_layernorm": false,
+ "model.layers.50.post_attention_layernorm": false,
+ "model.layers.51.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.51.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.51.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.51.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.51.self_attn.rope": false,
+ "model.layers.51.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.51.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.51.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.51.input_layernorm": false,
+ "model.layers.51.post_attention_layernorm": false,
+ "model.layers.52.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.52.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.self_attn.rope": false,
+ "model.layers.52.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.52.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.52.input_layernorm": false,
+ "model.layers.52.post_attention_layernorm": false,
+ "model.layers.53.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.53.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.53.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.53.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.53.self_attn.rope": false,
+ "model.layers.53.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.53.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.53.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.53.input_layernorm": false,
+ "model.layers.53.post_attention_layernorm": false,
+ "model.layers.54.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.54.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.54.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.54.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.54.self_attn.rope": false,
+ "model.layers.54.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.54.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.54.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.54.input_layernorm": false,
+ "model.layers.54.post_attention_layernorm": false,
+ "model.layers.55.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.55.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.self_attn.rope": false,
+ "model.layers.55.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.55.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.55.input_layernorm": false,
+ "model.layers.55.post_attention_layernorm": false,
+ "model.layers.56.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.56.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.self_attn.rope": false,
+ "model.layers.56.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.56.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.56.input_layernorm": false,
+ "model.layers.56.post_attention_layernorm": false,
+ "model.layers.57.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.57.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.self_attn.rope": false,
+ "model.layers.57.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.57.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.57.input_layernorm": false,
+ "model.layers.57.post_attention_layernorm": false,
+ "model.layers.58.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.58.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.self_attn.rope": false,
+ "model.layers.58.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.58.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.58.input_layernorm": false,
+ "model.layers.58.post_attention_layernorm": false,
+ "model.layers.59.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.59.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.self_attn.rope": false,
+ "model.layers.59.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.59.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.59.input_layernorm": false,
+ "model.layers.59.post_attention_layernorm": false,
+ "model.layers.60.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.60.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.self_attn.rope": false,
+ "model.layers.60.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.60.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.60.input_layernorm": false,
+ "model.layers.60.post_attention_layernorm": false,
+ "model.layers.61.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.61.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.self_attn.rope": false,
+ "model.layers.61.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.61.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.61.input_layernorm": false,
+ "model.layers.61.post_attention_layernorm": false,
+ "model.layers.62.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.62.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.self_attn.rope": false,
+ "model.layers.62.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.62.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.62.input_layernorm": false,
+ "model.layers.62.post_attention_layernorm": false,
+ "model.layers.63.self_attn.q_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.self_attn.k_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.self_attn.v_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.63.self_attn.o_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.self_attn.rope": false,
+ "model.layers.63.mlp.gate_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.mlp.down_proj": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "model.layers.63.mlp.up_proj": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "model.layers.63.input_layernorm": false,
+ "model.layers.63.post_attention_layernorm": false,
+ "model.norm": false,
+ "lm_head": {
+ "group_size": 64,
+ "bits": 8
+ }
+ },
+ "rms_norm_eps": 1e-05,
+ "rope_theta": 1000000.0,
+ "sliding_window": 131072,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.43.1",
+ "use_cache": true,
+ "use_sliding_window": false,
+ "vocab_size": 152064
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00001-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00001-of-00004.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a25dadeea2fd1bc5aa8d5629ec1f27ed52570c10
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00001-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7819f2c0378a7ea9896986fa6f2976101d6dd007bc5b22f5023a148d9a5617b6
+size 5321941889
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00002-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00002-of-00004.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..9eb340a7ed46748d80d946d4e121a19b3aef0dbb
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00002-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd4062e2e1a76c96699e2bdeaab15ce1a130f14f8ff3cc2625dc450e76bd3e96
+size 5363162608
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00003-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00003-of-00004.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..57d7b6c3c8d5c8c0727cc6690a1be3dee451daac
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00003-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a23c6fb10dca081039ccca54b9e4101820f55ad2669ba6db700e2d1bd54b81b1
+size 5357249052
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00004-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00004-of-00004.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2f8e4312262796c34de885c1e9c3f2d60c8d9847
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00004-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d849115b9ac769b41689460305df28026834a723b2bf002a132247ef170c09f9
+size 5127218901
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..9623ba03040e51c3bc211d6df7f30d896026d851
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model.safetensors.index.json
@@ -0,0 +1,1678 @@
+{
+ "metadata": {
+ "total_size": 21169383424
+ },
+ "weight_map": {
+ "lm_head.biases": "model-00004-of-00004.safetensors",
+ "lm_head.scales": "model-00004-of-00004.safetensors",
+ "lm_head.weight": "model-00004-of-00004.safetensors",
+ "model.embed_tokens.biases": "model-00001-of-00004.safetensors",
+ "model.embed_tokens.scales": "model-00001-of-00004.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.12.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.12.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.13.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.13.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.13.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.13.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.14.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.14.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.14.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.14.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.15.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.15.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.15.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.15.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.15.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.15.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.16.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.16.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.16.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.16.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.16.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.16.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.16.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.16.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.16.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.16.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.16.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.16.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.16.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.16.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.17.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.17.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.17.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.17.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.17.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.17.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.27.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.27.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.28.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.28.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.28.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.28.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.28.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.29.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.29.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.29.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.29.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.29.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.30.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.30.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.30.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.30.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.30.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.31.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.31.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.31.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.31.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.31.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.32.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.32.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.32.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.32.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.32.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.33.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.33.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.33.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.33.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.33.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.33.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.33.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.34.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.34.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.34.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.34.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.34.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.34.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.34.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.34.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.34.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.34.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.34.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.34.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.34.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.34.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.34.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.34.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.34.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.35.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.35.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.35.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.35.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.35.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.35.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.36.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.36.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.36.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.36.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.36.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.36.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.36.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.36.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.36.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.37.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.37.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.37.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.37.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.37.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.40.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.41.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.41.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.41.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.41.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.41.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.41.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.42.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.42.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.42.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.42.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.42.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.42.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.42.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.42.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.42.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.42.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.43.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.43.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.43.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.43.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.43.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.43.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.43.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.43.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.43.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.43.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.43.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.44.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.44.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.44.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.44.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.44.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.44.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.44.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.44.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.44.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.44.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.44.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.45.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.45.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.45.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.45.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.45.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.45.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.45.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.45.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.45.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.45.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.46.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.46.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.46.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.46.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.46.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.46.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.46.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.46.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.46.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.46.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.47.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.47.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.47.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.47.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.47.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.47.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.47.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.47.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.47.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.47.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.48.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.48.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.48.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.48.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.48.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.48.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.48.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.48.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.48.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.48.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.48.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.49.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.49.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.49.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.49.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.49.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.49.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.49.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.49.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.49.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.49.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.49.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.50.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.50.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.50.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.50.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.50.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.50.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.50.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.50.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.50.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.50.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.50.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.51.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.51.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.51.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.51.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.51.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.51.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.51.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.51.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.51.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.51.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.51.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.51.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.51.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.51.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.51.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.51.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.51.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.51.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.51.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.51.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.51.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.51.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.51.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.51.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.51.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.51.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.52.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.52.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.52.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.52.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.52.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.52.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.52.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.52.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.52.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.52.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.52.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.52.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.52.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.52.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.52.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.52.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.52.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.52.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.52.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.52.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.52.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.52.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.52.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.52.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.52.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.52.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.53.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.53.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.53.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.53.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.53.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.53.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.53.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.53.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.53.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.53.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.53.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.53.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.53.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.53.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.53.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.53.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.53.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.53.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.53.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.53.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.53.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.53.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.53.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.53.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.53.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.53.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.54.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.54.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.54.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.54.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.54.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.54.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.54.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.54.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.54.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.54.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.54.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.54.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.55.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.55.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.55.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.55.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.55.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.55.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.55.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.55.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.55.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.55.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.55.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.55.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.56.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.56.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.56.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.56.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.56.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.56.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.56.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.56.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.56.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.56.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.56.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.57.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.57.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.57.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.57.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.57.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.57.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.57.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.57.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.57.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.57.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.57.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.58.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.58.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.58.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.58.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.58.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.58.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.58.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.58.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.58.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.58.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.58.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.59.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.59.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.59.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.59.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.59.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.59.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.59.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.59.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.59.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.59.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.59.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.60.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.60.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.60.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.60.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.60.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.60.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.60.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.60.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.60.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.60.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.60.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.61.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.61.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.61.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.61.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.61.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.61.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.61.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.61.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.61.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.61.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.61.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.62.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.62.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.62.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.62.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.62.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.62.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.62.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.62.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.62.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.62.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.62.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.63.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.63.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.63.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.63.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.63.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.63.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.63.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.63.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.63.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.63.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.63.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.norm.weight": "model-00004-of-00004.safetensors"
+ }
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/tokenizer_config.json
@@ -0,0 +1,195 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4bit/config.json b/DeepSeek-R1-Distill-Qwen-32B-4bit/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..47b8b13a6df0f4d5d5b5cb47221674f6976b4e35
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-4bit/config.json
@@ -0,0 +1,35 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 5120,
+ "initializer_range": 0.02,
+ "intermediate_size": 27648,
+ "max_position_embeddings": 131072,
+ "max_window_layers": 64,
+ "model_type": "qwen2",
+ "num_attention_heads": 40,
+ "num_hidden_layers": 64,
+ "num_key_value_heads": 8,
+ "quantization": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "quantization_config": {
+ "group_size": 64,
+ "bits": 4
+ },
+ "rms_norm_eps": 1e-05,
+ "rope_theta": 1000000.0,
+ "sliding_window": 131072,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.43.1",
+ "use_cache": true,
+ "use_sliding_window": false,
+ "vocab_size": 152064
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4bit/model-00001-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B-4bit/model-00001-of-00004.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fa34e71491f43a26cdbfa600e69d3673f288be0c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-4bit/model-00001-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6f33ec1c4694317b3d5d6b224fe0910b9b372a3f16dac5bc55a1a88abfedd69
+size 5366582717
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4bit/model-00002-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B-4bit/model-00002-of-00004.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..38e9db4213b7c728854b9c804891c043859c007c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-4bit/model-00002-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7da76a1bbe610d1f2a4aab71ab77e78640cf382fb463a62584d9ac7b1864c395
+size 5335712972
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4bit/model-00003-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B-4bit/model-00003-of-00004.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a9eb93f124157eb85f3948c5a0fe6bc7809eef6f
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-4bit/model-00003-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0f9ca3c143151117f178ae23c2c8416cfe10a7e1d77e1fea1dd02be624236e6
+size 5366641944
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4bit/model-00004-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B-4bit/model-00004-of-00004.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5303714465d1557b9e56b06e35b9ddbba3fdd44c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-4bit/model-00004-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12390c345ed407188295fdd21290f536ac8d402aca0e9b72412d2c74092e1320
+size 2362540824
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4bit/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B-4bit/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..7949fa6067e06f908f1c2ec24cc73fc3c74bd9c7
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-4bit/model.safetensors.index.json
@@ -0,0 +1,1678 @@
+{
+ "metadata": {
+ "total_size": 18431289344
+ },
+ "weight_map": {
+ "lm_head.biases": "model-00004-of-00004.safetensors",
+ "lm_head.scales": "model-00004-of-00004.safetensors",
+ "lm_head.weight": "model-00004-of-00004.safetensors",
+ "model.embed_tokens.biases": "model-00001-of-00004.safetensors",
+ "model.embed_tokens.scales": "model-00001-of-00004.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.12.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.12.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.13.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.13.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.13.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.13.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.14.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.14.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.14.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.14.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.15.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.15.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.15.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.15.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.15.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.16.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.16.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.16.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.16.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.16.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.17.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.17.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.17.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.17.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.17.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.17.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.17.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.17.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.17.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.27.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.27.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.28.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.28.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.28.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.28.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.28.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.29.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.29.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.29.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.29.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.29.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.30.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.30.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.30.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.30.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.30.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.31.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.31.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.31.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.31.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.31.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.32.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.32.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.32.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.32.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.32.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.33.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.33.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.33.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.33.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.33.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.34.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.34.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.34.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.34.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.34.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.34.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.35.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.35.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.35.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.35.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.35.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.35.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.35.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.35.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.35.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.35.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.35.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.35.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.35.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.35.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.36.input_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.36.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.36.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.36.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.36.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.36.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.36.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.36.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.36.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+ "model.layers.36.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.36.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.36.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.36.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.36.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.36.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.36.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.36.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.36.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.36.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.36.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.37.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.37.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.37.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.37.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.37.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.37.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.37.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.37.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.37.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.37.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.37.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.37.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.37.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.37.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.37.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.37.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+ "model.layers.37.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+ "model.layers.37.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+ "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+ "model.layers.38.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.38.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.39.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.40.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.40.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.41.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.41.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.41.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.41.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.41.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.41.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.42.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.42.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.42.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.42.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.42.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.42.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.42.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.42.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.42.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.42.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.42.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.43.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.43.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.43.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.43.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.43.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.43.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.43.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.43.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.43.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.43.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.43.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.43.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.44.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.44.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.44.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.44.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.44.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.44.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.44.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.44.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.44.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.44.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.44.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.44.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.45.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.45.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.45.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.45.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.45.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.45.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.45.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.45.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.45.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.45.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.45.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.46.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.46.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.46.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.46.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.46.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.46.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.46.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.46.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.46.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.46.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.46.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.47.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.47.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.47.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.47.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.47.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.47.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.47.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.47.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.47.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.47.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.47.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.48.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.48.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.48.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.48.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.48.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.48.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.48.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.48.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.48.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.48.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.48.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.48.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.49.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.49.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.49.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.49.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.49.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.49.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.49.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.49.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.49.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.49.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.49.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.49.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.50.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.50.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.50.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.50.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.50.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.50.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.50.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.50.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.50.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.50.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.50.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.50.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.51.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.51.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.51.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.51.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.51.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.51.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.51.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.51.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.51.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.51.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.51.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.51.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.52.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.52.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.52.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.52.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.52.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.52.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.52.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.52.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.52.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.52.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.52.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.52.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.53.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.53.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.53.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.53.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.53.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.53.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.53.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.53.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.53.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.53.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.53.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.53.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.54.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.54.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.54.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.54.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.54.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.54.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.54.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.54.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.54.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.54.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.54.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.54.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.54.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.54.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.54.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.54.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.54.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.54.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.54.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.54.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.54.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.54.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.54.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.54.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.54.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.54.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.55.input_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.55.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.55.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.55.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.55.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.55.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.55.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.55.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.55.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.55.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.55.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+ "model.layers.55.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.55.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.55.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.55.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.55.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.55.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.55.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.55.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.55.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.55.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.55.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.55.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.55.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.55.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.55.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.56.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.56.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.56.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.56.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.56.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.56.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.56.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.56.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.56.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.56.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.56.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.56.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.56.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.56.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.56.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.56.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.56.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.56.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.56.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.56.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.56.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.56.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.56.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+ "model.layers.56.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+ "model.layers.56.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+ "model.layers.56.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+ "model.layers.57.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.57.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.57.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.57.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.57.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.57.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.57.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.57.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.57.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.57.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.57.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.57.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.58.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.58.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.58.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.58.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.58.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.58.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.58.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.58.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.58.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.58.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.58.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.58.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.59.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.59.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.59.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.59.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.59.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.59.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.59.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.59.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.59.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.59.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.59.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.59.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.60.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.60.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.60.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.60.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.60.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.60.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.60.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.60.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.60.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.60.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.60.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.60.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.61.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.61.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.61.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.61.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.61.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.61.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.61.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.61.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.61.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.61.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.61.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.61.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.62.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.62.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.62.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.62.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.62.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.62.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.62.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.62.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.62.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.62.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.62.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.62.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.63.input_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.63.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.63.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.63.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.63.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.63.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.63.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.63.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.63.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.63.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.63.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+ "model.layers.63.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+ "model.norm.weight": "model-00004-of-00004.safetensors"
+ }
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4bit/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B-4bit/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-4bit/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4bit/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B-4bit/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-4bit/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-32B-4bit/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B-4bit/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-4bit/tokenizer_config.json
@@ -0,0 +1,195 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/config.json b/DeepSeek-R1-Distill-Qwen-32B-6bit/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1ae0ef50e634d8a07427dc5e1136746dd21473ac
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-6bit/config.json
@@ -0,0 +1,35 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 5120,
+ "initializer_range": 0.02,
+ "intermediate_size": 27648,
+ "max_position_embeddings": 131072,
+ "max_window_layers": 64,
+ "model_type": "qwen2",
+ "num_attention_heads": 40,
+ "num_hidden_layers": 64,
+ "num_key_value_heads": 8,
+ "quantization": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "quantization_config": {
+ "group_size": 64,
+ "bits": 6
+ },
+ "rms_norm_eps": 1e-05,
+ "rope_theta": 1000000.0,
+ "sliding_window": 131072,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.43.1",
+ "use_cache": true,
+ "use_sliding_window": false,
+ "vocab_size": 152064
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00001-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00001-of-00006.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..bd50ccc10416b584575792d741743e4ffa7d2286
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00001-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a00935ed67ac7e66d142d5f9e4815eb8ab3f961faa7b8bcbca55a4ff2f4ee25
+size 5271984209
diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00002-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00002-of-00006.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..35b735b757d7980e58f65e1311d988d9e7d75de9
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00002-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e09753f33189775b86554c9737eb5574dbd556dd476966ee69cccdb0eb89517
+size 5316808320
diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00003-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00003-of-00006.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..37d4cdd24df8ae7e352ca68c2cc7849c9a6a4446
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00003-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c40d6060b390eac2274cb2d18973e8fc4ef5747e4d5ae60b2c7a6f0fc8505fb
+size 5265653517
diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00004-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00004-of-00006.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ff80a953c7723fc0cae5770b20b55c43de3b976f
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00004-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f81a6a9069dda4ded4f7043ef63966d113d9534180fa561fa25ffa21ab646479
+size 5265653541
diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00005-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00005-of-00006.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d136bca71b10ba8fe0ad61f039b66a331935d7a3
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00005-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a88fe01f535a1e4316b000d0f5322482e33e598003500c39bf174a4cee86ed1
+size 4869481603
diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00006-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00006-of-00006.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a8676dc07afffbbc5fe7b41db3ad6d308576b05b
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00006-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04c494df573aaf13437bb7e389e37e2ab8b602836efb826cb3178bf4b125d1e0
+size 632586540
diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B-6bit/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..b5e942aa358d06cce6e319fcc937a4e0a92158ac
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-6bit/model.safetensors.index.json
@@ -0,0 +1,1678 @@
+{
+ "metadata": {
+ "total_size": 26621978624
+ },
+ "weight_map": {
+ "lm_head.biases": "model-00006-of-00006.safetensors",
+ "lm_head.scales": "model-00006-of-00006.safetensors",
+ "lm_head.weight": "model-00006-of-00006.safetensors",
+ "model.embed_tokens.biases": "model-00001-of-00006.safetensors",
+ "model.embed_tokens.scales": "model-00001-of-00006.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.mlp.down_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.mlp.up_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.mlp.down_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.mlp.up_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.10.mlp.down_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.10.mlp.down_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.10.mlp.up_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.10.mlp.up_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.mlp.down_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.11.mlp.down_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.11.mlp.up_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.11.mlp.up_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.mlp.down_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.12.mlp.down_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.12.mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.mlp.up_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.12.mlp.up_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.mlp.down_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.13.mlp.down_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.13.mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.mlp.up_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.13.mlp.up_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.14.mlp.down_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.14.mlp.down_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.14.mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.14.mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.14.mlp.up_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.14.mlp.up_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.15.mlp.down_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.15.mlp.down_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.15.mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.15.mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.15.mlp.up_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.15.mlp.up_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.16.mlp.down_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.16.mlp.down_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.16.mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.16.mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.16.mlp.up_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.16.mlp.up_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.16.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.16.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.16.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.16.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.16.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.16.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.16.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.16.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.17.mlp.down_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.17.mlp.down_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.17.mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.17.mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.17.mlp.up_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.17.mlp.up_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.17.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.17.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.17.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.17.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.17.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.17.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.17.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.17.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.18.mlp.down_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.18.mlp.down_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.18.mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.18.mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.18.mlp.up_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.18.mlp.up_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.18.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.18.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.18.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.18.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.18.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.18.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.18.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.19.mlp.down_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.19.mlp.down_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.19.mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.19.mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.19.mlp.up_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.19.mlp.up_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.19.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.19.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.19.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.19.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.19.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.19.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.19.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.19.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.mlp.down_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.mlp.up_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.20.mlp.down_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.20.mlp.down_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.20.mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.20.mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.20.mlp.up_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.20.mlp.up_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.20.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.20.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.20.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.20.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.20.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.20.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.20.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.20.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.21.mlp.down_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.21.mlp.down_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.21.mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.21.mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.21.mlp.up_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.21.mlp.up_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.21.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.21.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.21.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.21.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.21.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.21.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.21.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.21.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.22.mlp.down_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.22.mlp.down_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.22.mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.22.mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.22.mlp.up_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.22.mlp.up_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.22.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.22.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.22.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.22.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.22.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.22.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.22.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.22.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.23.mlp.down_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.23.mlp.down_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.23.mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.23.mlp.up_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.23.mlp.up_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.23.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.23.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.23.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.23.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.24.mlp.down_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.24.mlp.down_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.24.mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.24.mlp.up_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.24.mlp.up_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.24.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.24.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.24.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.24.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.25.mlp.down_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.25.mlp.down_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.25.mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.25.mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.25.mlp.up_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.25.mlp.up_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.25.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.25.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.25.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.25.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
+ "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.26.mlp.down_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.26.mlp.down_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.26.mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.26.mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.26.mlp.up_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.26.mlp.up_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.26.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.26.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.26.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.26.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.26.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.26.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.26.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.26.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.27.mlp.down_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.27.mlp.down_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.27.mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.27.mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.27.mlp.up_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.27.mlp.up_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.27.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.27.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.27.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.27.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.27.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.27.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.27.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.27.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.28.mlp.down_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.28.mlp.down_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.28.mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.28.mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.28.mlp.up_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.28.mlp.up_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.28.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.28.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.28.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.28.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.28.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.28.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.28.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.28.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.28.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.28.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.28.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.29.mlp.down_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.29.mlp.down_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.29.mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.29.mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.29.mlp.up_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.29.mlp.up_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.29.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.29.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.29.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.29.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.29.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.29.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.29.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.29.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.29.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.29.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.29.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.mlp.down_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.mlp.up_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.30.mlp.down_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.30.mlp.down_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.30.mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.30.mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.30.mlp.up_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.30.mlp.up_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.30.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.30.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.30.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.30.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.30.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.30.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.30.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.30.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.30.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.30.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.30.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.31.mlp.down_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.31.mlp.down_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.31.mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.31.mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.31.mlp.up_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.31.mlp.up_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.31.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.31.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.31.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.31.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.31.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.31.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.31.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.31.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.31.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.31.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.31.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.32.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.32.mlp.down_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.32.mlp.down_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.32.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.32.mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.32.mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.32.mlp.up_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.32.mlp.up_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.32.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.32.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.32.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.32.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.32.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.32.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.32.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.32.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.32.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.32.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.32.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.32.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.33.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.33.mlp.down_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.33.mlp.down_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.33.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.33.mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.33.mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.33.mlp.up_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.33.mlp.up_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.33.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.33.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.33.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.33.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.33.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.33.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.33.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.33.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.33.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.33.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.33.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.33.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.34.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.34.mlp.down_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.34.mlp.down_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.34.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.34.mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.34.mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.34.mlp.up_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.34.mlp.up_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.34.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.34.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.34.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.34.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.34.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.34.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.34.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.34.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.34.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.34.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.34.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.34.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.35.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.35.mlp.down_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.35.mlp.down_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.35.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.35.mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.35.mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.35.mlp.up_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.35.mlp.up_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.35.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.35.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.35.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.35.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.35.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.35.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.35.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.35.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.35.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.35.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.35.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.35.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.36.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.36.mlp.down_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.36.mlp.down_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.36.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.36.mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.36.mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.36.mlp.up_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.36.mlp.up_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.36.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.36.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.36.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.36.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.36.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.36.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.36.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.36.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.36.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.36.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.36.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.36.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.37.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.37.mlp.down_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.37.mlp.down_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.37.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.37.mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.37.mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.37.mlp.up_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.37.mlp.up_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.37.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.37.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.37.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.37.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.37.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.37.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.37.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.37.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.37.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.37.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.37.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.37.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.38.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.38.mlp.down_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.38.mlp.down_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.38.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.38.mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.38.mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.38.mlp.up_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.38.mlp.up_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.38.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.38.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.38.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.38.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.38.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.38.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.38.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.38.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.38.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.38.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.38.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
+ "model.layers.38.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
+ "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.39.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.39.mlp.down_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.39.mlp.down_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.39.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.39.mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.39.mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.39.mlp.up_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.39.mlp.up_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.39.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.39.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.39.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.39.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.39.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.39.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.39.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.39.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.39.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.39.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.39.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.39.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.mlp.down_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.mlp.up_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.40.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.40.mlp.down_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.40.mlp.down_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.40.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.40.mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.40.mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.40.mlp.up_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.40.mlp.up_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.40.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.40.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.40.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.40.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.40.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.40.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.40.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.40.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.40.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.40.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.40.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.40.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.41.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.41.mlp.down_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.41.mlp.down_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.41.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.41.mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.41.mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.41.mlp.up_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.41.mlp.up_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.41.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.41.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.41.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.41.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.41.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.41.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.41.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.41.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.41.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.41.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.41.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.41.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.42.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.42.mlp.down_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.42.mlp.down_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.42.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.42.mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.42.mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.42.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.42.mlp.up_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.42.mlp.up_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.42.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.42.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.42.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.42.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.42.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.42.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.42.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.42.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.42.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.42.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.42.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.42.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.42.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.42.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.42.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.42.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.42.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.43.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.43.mlp.down_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.43.mlp.down_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.43.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.43.mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.43.mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.43.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.43.mlp.up_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.43.mlp.up_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.43.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.43.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.43.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.43.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.43.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.43.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.43.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.43.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.43.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.43.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.43.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.43.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.43.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.43.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.43.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.43.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.44.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.44.mlp.down_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.44.mlp.down_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.44.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.44.mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.44.mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.44.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.44.mlp.up_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.44.mlp.up_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.44.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.44.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.44.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.44.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.44.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.44.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.44.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.44.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.44.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.44.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.44.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.44.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.44.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.44.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.44.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.44.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.44.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.45.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.45.mlp.down_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.45.mlp.down_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.45.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.45.mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.45.mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.45.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.45.mlp.up_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.45.mlp.up_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.45.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.45.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.45.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.45.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.45.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.45.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.45.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.45.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.45.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.45.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.45.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.45.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.45.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.45.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.45.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.45.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.45.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.46.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.46.mlp.down_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.46.mlp.down_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.46.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.46.mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.46.mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.46.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.46.mlp.up_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.46.mlp.up_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.46.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.46.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.46.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.46.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.46.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.46.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.46.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.46.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.46.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.46.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.46.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.46.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.46.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.46.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.46.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.46.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.46.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.47.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.47.mlp.down_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.47.mlp.down_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.47.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.47.mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.47.mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.47.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.47.mlp.up_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.47.mlp.up_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.47.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.47.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.47.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.47.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.47.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.47.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.47.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.47.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.47.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.47.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.47.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.47.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.47.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.47.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.47.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.47.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.47.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.48.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.48.mlp.down_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.48.mlp.down_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.48.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.48.mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.48.mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.48.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.48.mlp.up_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.48.mlp.up_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.48.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.48.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.48.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.48.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.48.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.48.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.48.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.48.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.48.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.48.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.48.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.48.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.48.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.48.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.48.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.48.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.48.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.49.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.49.mlp.down_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.49.mlp.down_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.49.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.49.mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.49.mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.49.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.49.mlp.up_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.49.mlp.up_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.49.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.49.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.49.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.49.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.49.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.49.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.49.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.49.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.49.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.49.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.49.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.49.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.49.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.49.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.49.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.49.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.49.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.5.mlp.down_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.5.mlp.up_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.50.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.50.mlp.down_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.50.mlp.down_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.50.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.50.mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.50.mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.50.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.50.mlp.up_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.50.mlp.up_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.50.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.50.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.50.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.50.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.50.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.50.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.50.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.50.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.50.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.50.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.50.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.50.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.50.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.50.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.50.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.50.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.50.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.51.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.51.mlp.down_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.51.mlp.down_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.51.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.51.mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.51.mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.51.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.51.mlp.up_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.51.mlp.up_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.51.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.51.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.51.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.51.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.51.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.51.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.51.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.51.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.51.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.51.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.51.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.51.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.51.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.51.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.51.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
+ "model.layers.51.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
+ "model.layers.51.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.52.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.52.mlp.down_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.52.mlp.down_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.52.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.52.mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.52.mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.52.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.52.mlp.up_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.52.mlp.up_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.52.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.52.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.52.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.52.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.52.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.52.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.52.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.52.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.52.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.52.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.52.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.52.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.52.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.52.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.52.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.52.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.52.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.53.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.53.mlp.down_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.53.mlp.down_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.53.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.53.mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.53.mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.53.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.53.mlp.up_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.53.mlp.up_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.53.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.53.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.53.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.53.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.53.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.53.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.53.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.53.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.53.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.53.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.53.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.53.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.53.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.53.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.53.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.53.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.53.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.54.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.54.mlp.down_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.54.mlp.down_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.54.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.54.mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.54.mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.54.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.54.mlp.up_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.54.mlp.up_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.54.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.54.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.54.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.54.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.54.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.54.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.54.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.54.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.54.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.54.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.54.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.54.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.54.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.54.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.54.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.54.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.54.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.55.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.55.mlp.down_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.55.mlp.down_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.55.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.55.mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.55.mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.55.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.55.mlp.up_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.55.mlp.up_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.55.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.55.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.55.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.55.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.55.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.55.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.55.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.55.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.55.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.55.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.55.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.55.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.55.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.55.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.55.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.55.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.55.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.56.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.56.mlp.down_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.56.mlp.down_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.56.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.56.mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.56.mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.56.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.56.mlp.up_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.56.mlp.up_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.56.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.56.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.56.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.56.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.56.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.56.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.56.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.56.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.56.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.56.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.56.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.56.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.56.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.56.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.56.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.56.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.56.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.57.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.57.mlp.down_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.57.mlp.down_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.57.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.57.mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.57.mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.57.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.57.mlp.up_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.57.mlp.up_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.57.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.57.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.57.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.57.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.57.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.57.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.57.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.57.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.57.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.57.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.57.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.57.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.57.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.57.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.57.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.57.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.57.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.58.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.58.mlp.down_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.58.mlp.down_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.58.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.58.mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.58.mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.58.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.58.mlp.up_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.58.mlp.up_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.58.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.58.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.58.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.58.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.58.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.58.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.58.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.58.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.58.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.58.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.58.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.58.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.58.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.58.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.58.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.58.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.58.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.59.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.59.mlp.down_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.59.mlp.down_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.59.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.59.mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.59.mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.59.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.59.mlp.up_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.59.mlp.up_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.59.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.59.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.59.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.59.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.59.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.59.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.59.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.59.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.59.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.59.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.59.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.59.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.59.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.59.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.59.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.59.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.59.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.6.mlp.down_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.6.mlp.up_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.60.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.60.mlp.down_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.60.mlp.down_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.60.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.60.mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.60.mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.60.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.60.mlp.up_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.60.mlp.up_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.60.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.60.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.60.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.60.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.60.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.60.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.60.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.60.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.60.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.60.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.60.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.60.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.60.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.60.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.60.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.60.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.60.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.61.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.61.mlp.down_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.61.mlp.down_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.61.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.61.mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.61.mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.61.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.61.mlp.up_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.61.mlp.up_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.61.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.61.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.61.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.61.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.61.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.61.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.61.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.61.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.61.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.61.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.61.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.61.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.61.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.61.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.61.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.61.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.61.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.62.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.62.mlp.down_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.62.mlp.down_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.62.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.62.mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.62.mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.62.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.62.mlp.up_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.62.mlp.up_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.62.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.62.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.62.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.62.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.62.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.62.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.62.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.62.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.62.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.62.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.62.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.62.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.62.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.62.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.62.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.62.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.62.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.63.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.63.mlp.down_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.63.mlp.down_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.63.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.63.mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.63.mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.63.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.63.mlp.up_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.63.mlp.up_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.63.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.63.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.63.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.63.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.63.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.63.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.63.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.63.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.63.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.63.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.63.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.63.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.63.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.63.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.63.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
+ "model.layers.63.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
+ "model.layers.63.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.7.mlp.down_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.7.mlp.up_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.8.mlp.down_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.8.mlp.up_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.8.mlp.up_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.9.mlp.down_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.9.mlp.down_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.9.mlp.up_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.9.mlp.up_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
+ "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.norm.weight": "model-00005-of-00006.safetensors"
+ }
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B-6bit/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-6bit/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B-6bit/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-6bit/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B-6bit/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-6bit/tokenizer_config.json
@@ -0,0 +1,195 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/config.json b/DeepSeek-R1-Distill-Qwen-32B-8bit/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..9739a1aa9f8d7a19f46016b2bb951fc94337af27
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-8bit/config.json
@@ -0,0 +1,35 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 5120,
+ "initializer_range": 0.02,
+ "intermediate_size": 27648,
+ "max_position_embeddings": 131072,
+ "max_window_layers": 64,
+ "model_type": "qwen2",
+ "num_attention_heads": 40,
+ "num_hidden_layers": 64,
+ "num_key_value_heads": 8,
+ "quantization": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "quantization_config": {
+ "group_size": 64,
+ "bits": 8
+ },
+ "rms_norm_eps": 1e-05,
+ "rope_theta": 1000000.0,
+ "sliding_window": 131072,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.43.1",
+ "use_cache": true,
+ "use_sliding_window": false,
+ "vocab_size": 152064
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00001-of-00007.safetensors b/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00001-of-00007.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..9808909775cdd67c78f3a9d654e8169afa847add
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00001-of-00007.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f49f3c007b150fac67e909703d4c80223091b1df5c89f925eb56d03f77128ec
+size 5339700785
diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00002-of-00007.safetensors b/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00002-of-00007.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b825fffa5f134ec6b827f3b27df02813ee80c970
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00002-of-00007.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed1608e9292d3d14e98226291362dedac258b3f14cc1c0ece7cd3c797ff1b0c4
+size 5364861187
diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00003-of-00007.safetensors b/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00003-of-00007.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..77e53de96ea8ece9beed4a833e8da1acae9ad793
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00003-of-00007.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7878ee4f5cbb3e15757a7e4f95d4fa1d034ff7a988e3daadb030f448da0ccce9
+size 5364830173
diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00004-of-00007.safetensors b/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00004-of-00007.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4def0752bd15fc674a9bdfe0fe6253abe1b8a74c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00004-of-00007.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a80fef18c69aee587c2f5490988e9d0de9313c2e542a34b6a37a359211749f1d
+size 5331404024
diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00005-of-00007.safetensors b/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00005-of-00007.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a30be962265eaa51571b0b3c6a7bffd7f58457b6
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00005-of-00007.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49cf366d67b61a144e4afa4413250331adec2893a6dc0d72ae891748bf398c68
+size 5364861246
diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00006-of-00007.safetensors b/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00006-of-00007.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..dec9cce32318be547ef672ea901f9a2d60d7f86d
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00006-of-00007.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d91a1d6d78354bc4a9ee2c9008c606e2033a078ec0b62e701378a66355b177e
+size 5364830197
diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00007-of-00007.safetensors b/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00007-of-00007.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ce8b895cafe1f879138bd77e752783cf8f30e694
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00007-of-00007.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec29dea35ff6a109994e8199585b7264c37f2d653fb17a0e0d752e77de7d2bf4
+size 2682369911
diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B-8bit/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..d5b2be0027e822f018604558746e44a538b7d292
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-8bit/model.safetensors.index.json
@@ -0,0 +1,1678 @@
+{
+ "metadata": {
+ "total_size": 34812667904
+ },
+ "weight_map": {
+ "lm_head.biases": "model-00007-of-00007.safetensors",
+ "lm_head.scales": "model-00007-of-00007.safetensors",
+ "lm_head.weight": "model-00007-of-00007.safetensors",
+ "model.embed_tokens.biases": "model-00001-of-00007.safetensors",
+ "model.embed_tokens.scales": "model-00001-of-00007.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+ "model.layers.0.mlp.down_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.0.mlp.up_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+ "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+ "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+ "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+ "model.layers.1.mlp.down_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.1.mlp.up_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+ "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+ "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+ "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.10.mlp.down_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.10.mlp.down_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.10.mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.10.mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.10.mlp.up_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.10.mlp.up_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.10.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.10.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.10.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.10.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.10.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.10.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.10.self_attn.v_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.10.self_attn.v_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.11.mlp.down_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.11.mlp.down_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.11.mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.11.mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.11.mlp.up_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.11.mlp.up_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.11.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.11.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.11.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.11.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.11.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.11.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.11.self_attn.v_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.11.self_attn.v_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.12.mlp.down_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.12.mlp.down_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.12.mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.12.mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.12.mlp.up_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.12.mlp.up_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.12.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.12.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.12.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.12.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.12.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.12.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.12.self_attn.v_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.12.self_attn.v_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.13.mlp.down_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.13.mlp.down_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.13.mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.13.mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.13.mlp.up_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.13.mlp.up_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.13.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.13.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.13.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.13.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.13.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.13.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.13.self_attn.v_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.13.self_attn.v_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.14.mlp.down_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.14.mlp.down_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.14.mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.14.mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.14.mlp.up_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.14.mlp.up_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.14.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.14.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.14.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.14.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.14.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.14.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.14.self_attn.v_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.14.self_attn.v_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.15.mlp.down_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.15.mlp.down_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.15.mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.15.mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.15.mlp.up_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.15.mlp.up_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.15.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.15.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.15.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.15.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.15.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.15.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.15.self_attn.v_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.15.self_attn.v_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.16.mlp.down_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.16.mlp.down_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.16.mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.16.mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.16.mlp.up_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.16.mlp.up_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.16.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.16.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.16.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.16.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.16.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.16.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.16.self_attn.v_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.16.self_attn.v_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.17.mlp.down_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.17.mlp.down_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.17.mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.17.mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.17.mlp.up_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.17.mlp.up_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.17.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.17.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.17.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.17.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.17.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.17.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.17.self_attn.v_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.17.self_attn.v_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.18.mlp.down_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.18.mlp.down_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.18.mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.18.mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.18.mlp.up_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.18.mlp.up_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.18.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.18.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.18.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.18.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.18.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.18.self_attn.v_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.18.self_attn.v_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.19.mlp.down_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.19.mlp.down_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.19.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.19.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.19.mlp.up_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.19.mlp.up_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.19.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.19.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.19.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.19.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.19.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.19.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.19.self_attn.v_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.19.self_attn.v_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+ "model.layers.2.mlp.down_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.2.mlp.up_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+ "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+ "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+ "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.20.mlp.down_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.20.mlp.down_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.20.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.20.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.20.mlp.up_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.20.mlp.up_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.20.self_attn.k_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.20.self_attn.k_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.20.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.20.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.20.self_attn.q_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.20.self_attn.q_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.20.self_attn.v_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.20.self_attn.v_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.21.mlp.down_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.21.mlp.down_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.21.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.21.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.21.mlp.up_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.21.mlp.up_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.21.self_attn.k_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.21.self_attn.k_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.21.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.21.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.21.self_attn.q_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.21.self_attn.q_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.21.self_attn.v_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.21.self_attn.v_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.22.mlp.down_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.22.mlp.down_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.22.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.22.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.22.mlp.up_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.22.mlp.up_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.22.self_attn.k_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.22.self_attn.k_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.22.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.22.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.22.self_attn.q_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.22.self_attn.q_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.22.self_attn.v_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.22.self_attn.v_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.23.mlp.down_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.23.mlp.down_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.23.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.23.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.23.mlp.up_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.23.mlp.up_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.23.self_attn.k_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.23.self_attn.k_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.23.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.23.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.23.self_attn.q_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.23.self_attn.q_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.23.self_attn.v_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.23.self_attn.v_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.24.mlp.down_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.24.mlp.down_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.24.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.24.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.24.mlp.up_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.24.mlp.up_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.24.self_attn.k_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.24.self_attn.k_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.24.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.24.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.24.self_attn.q_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.24.self_attn.q_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.24.self_attn.v_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.24.self_attn.v_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.25.mlp.down_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.25.mlp.down_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.25.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.25.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.25.mlp.up_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.25.mlp.up_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.25.self_attn.k_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.25.self_attn.k_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.25.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.25.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.25.self_attn.q_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.25.self_attn.q_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.25.self_attn.v_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.25.self_attn.v_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.26.mlp.down_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.26.mlp.down_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.26.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.26.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.26.mlp.up_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.26.mlp.up_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.26.self_attn.k_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.26.self_attn.k_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.26.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.26.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.26.self_attn.q_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.26.self_attn.q_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.26.self_attn.v_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.26.self_attn.v_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.27.mlp.down_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.27.mlp.down_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.27.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.27.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.27.mlp.up_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.27.mlp.up_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.27.self_attn.k_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.27.self_attn.k_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.27.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.27.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.27.self_attn.q_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.27.self_attn.q_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.27.self_attn.v_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.27.self_attn.v_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.28.mlp.down_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.28.mlp.down_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.28.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.28.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.28.mlp.up_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.28.mlp.up_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.28.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.28.self_attn.k_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.28.self_attn.k_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.28.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.28.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.28.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.28.self_attn.q_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.28.self_attn.q_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.28.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.28.self_attn.v_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.28.self_attn.v_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.29.input_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.29.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.29.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.29.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.29.mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.29.mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.29.mlp.up_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.29.mlp.up_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.29.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.29.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.29.self_attn.k_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.29.self_attn.k_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.29.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.29.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.29.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.29.self_attn.q_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.29.self_attn.q_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.29.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+ "model.layers.29.self_attn.v_proj.biases": "model-00003-of-00007.safetensors",
+ "model.layers.29.self_attn.v_proj.scales": "model-00003-of-00007.safetensors",
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
+ "model.layers.3.mlp.down_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.3.mlp.up_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+ "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+ "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+ "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.30.input_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.30.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.30.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.30.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.30.mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.30.mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.30.mlp.up_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.30.mlp.up_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.30.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.30.self_attn.k_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.30.self_attn.k_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.30.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.30.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.30.self_attn.q_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.30.self_attn.q_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.30.self_attn.v_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.30.self_attn.v_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.31.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.31.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.31.mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.31.mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.31.mlp.up_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.31.mlp.up_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.31.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.31.self_attn.k_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.31.self_attn.k_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.31.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.31.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.31.self_attn.q_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.31.self_attn.q_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.31.self_attn.v_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.31.self_attn.v_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.32.input_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.32.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.32.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.32.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.32.mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.32.mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.32.mlp.up_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.32.mlp.up_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.32.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.32.self_attn.k_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.32.self_attn.k_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.32.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.32.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.32.self_attn.q_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.32.self_attn.q_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.32.self_attn.v_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.32.self_attn.v_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.33.input_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.33.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.33.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.33.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.33.mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.33.mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.33.mlp.up_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.33.mlp.up_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.33.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.33.self_attn.k_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.33.self_attn.k_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.33.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.33.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.33.self_attn.q_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.33.self_attn.q_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.33.self_attn.v_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.33.self_attn.v_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.34.input_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.34.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.34.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.34.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.34.mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.34.mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.34.mlp.up_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.34.mlp.up_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.34.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.34.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.34.self_attn.k_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.34.self_attn.k_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.34.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.34.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.34.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.34.self_attn.q_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.34.self_attn.q_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.34.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.34.self_attn.v_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.34.self_attn.v_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.35.input_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.35.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.35.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.35.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.35.mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.35.mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.35.mlp.up_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.35.mlp.up_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.35.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.35.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.35.self_attn.k_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.35.self_attn.k_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.35.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.35.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.35.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.35.self_attn.q_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.35.self_attn.q_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.35.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.35.self_attn.v_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.35.self_attn.v_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.36.input_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.36.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.36.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.36.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.36.mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.36.mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.36.mlp.up_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.36.mlp.up_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.36.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.36.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.36.self_attn.k_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.36.self_attn.k_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.36.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.36.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.36.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.36.self_attn.q_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.36.self_attn.q_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.36.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.36.self_attn.v_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.36.self_attn.v_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.37.input_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.37.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.37.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.37.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.37.mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.37.mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.37.mlp.up_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.37.mlp.up_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.37.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.37.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.37.self_attn.k_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.37.self_attn.k_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.37.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.37.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.37.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.37.self_attn.q_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.37.self_attn.q_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.37.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.37.self_attn.v_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.37.self_attn.v_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.38.input_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.38.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.38.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.38.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.38.mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.38.mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.38.mlp.up_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.38.mlp.up_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.38.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.38.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.38.self_attn.k_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.38.self_attn.k_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.38.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.38.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.38.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.38.self_attn.q_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.38.self_attn.q_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.38.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.38.self_attn.v_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.38.self_attn.v_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.39.input_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.39.mlp.down_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.39.mlp.down_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.39.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.39.mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.39.mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.39.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.39.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.39.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.39.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.39.self_attn.k_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.39.self_attn.k_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.39.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.39.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.39.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.39.self_attn.q_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.39.self_attn.q_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.39.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+ "model.layers.39.self_attn.v_proj.biases": "model-00004-of-00007.safetensors",
+ "model.layers.39.self_attn.v_proj.scales": "model-00004-of-00007.safetensors",
+ "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
+ "model.layers.4.mlp.down_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.4.mlp.up_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+ "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+ "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+ "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.40.input_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.40.mlp.down_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.40.mlp.down_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.40.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.40.mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.40.mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.40.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.40.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.40.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.40.self_attn.k_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.40.self_attn.k_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.40.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.40.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.40.self_attn.q_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.40.self_attn.q_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.40.self_attn.v_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.40.self_attn.v_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.41.input_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.41.mlp.down_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.41.mlp.down_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.41.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.41.mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.41.mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.41.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.41.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.41.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.41.self_attn.k_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.41.self_attn.k_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.41.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.41.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.41.self_attn.q_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.41.self_attn.q_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.41.self_attn.v_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.41.self_attn.v_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.42.input_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.42.mlp.down_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.42.mlp.down_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.42.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.42.mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.42.mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.42.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.42.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.42.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.42.self_attn.k_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.42.self_attn.k_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.42.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.42.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.42.self_attn.q_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.42.self_attn.q_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.42.self_attn.v_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.42.self_attn.v_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.43.input_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.43.mlp.down_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.43.mlp.down_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.43.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.43.mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.43.mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.43.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.43.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.43.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.43.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.43.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.43.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.43.self_attn.k_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.43.self_attn.k_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.43.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.43.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.43.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.43.self_attn.q_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.43.self_attn.q_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.43.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.43.self_attn.v_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.43.self_attn.v_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.44.input_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.44.mlp.down_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.44.mlp.down_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.44.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.44.mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.44.mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.44.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.44.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.44.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.44.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.44.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.44.self_attn.k_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.44.self_attn.k_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.44.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.44.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.44.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.44.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.44.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.44.self_attn.q_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.44.self_attn.q_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.44.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.44.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.44.self_attn.v_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.44.self_attn.v_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.44.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.45.input_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.45.mlp.down_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.45.mlp.down_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.45.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.45.mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.45.mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.45.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.45.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.45.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.45.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.45.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.45.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.45.self_attn.k_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.45.self_attn.k_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.45.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.45.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.45.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.45.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.45.self_attn.q_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.45.self_attn.q_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.45.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.45.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.45.self_attn.v_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.45.self_attn.v_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.45.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.46.input_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.46.mlp.down_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.46.mlp.down_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.46.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.46.mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.46.mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.46.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.46.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.46.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.46.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.46.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.46.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.46.self_attn.k_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.46.self_attn.k_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.46.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.46.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.46.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.46.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.46.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.46.self_attn.q_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.46.self_attn.q_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.46.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.46.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.46.self_attn.v_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.46.self_attn.v_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.46.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.47.input_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.47.mlp.down_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.47.mlp.down_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.47.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.47.mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.47.mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.47.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.47.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.47.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.47.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.47.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.47.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.47.self_attn.k_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.47.self_attn.k_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.47.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.47.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.47.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.47.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.47.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.47.self_attn.q_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.47.self_attn.q_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.47.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.47.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.47.self_attn.v_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.47.self_attn.v_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.47.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.48.input_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.48.mlp.down_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.48.mlp.down_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.48.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.48.mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.48.mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.48.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.48.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.48.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.48.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.48.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.48.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.48.self_attn.k_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.48.self_attn.k_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.48.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.48.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.48.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.48.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.48.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.48.self_attn.q_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.48.self_attn.q_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.48.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.48.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.48.self_attn.v_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.48.self_attn.v_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.48.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.49.input_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.49.mlp.down_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.49.mlp.down_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.49.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.49.mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.49.mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.49.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.49.mlp.up_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.49.mlp.up_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.49.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.49.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.49.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.49.self_attn.k_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.49.self_attn.k_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.49.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.49.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.49.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.49.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.49.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.49.self_attn.q_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.49.self_attn.q_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.49.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.49.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.49.self_attn.v_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.49.self_attn.v_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.49.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors",
+ "model.layers.5.mlp.down_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.5.mlp.up_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+ "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+ "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+ "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.50.input_layernorm.weight": "model-00006-of-00007.safetensors",
+ "model.layers.50.mlp.down_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.50.mlp.down_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.50.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.50.mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.50.mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.50.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.50.mlp.up_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.50.mlp.up_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.50.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.50.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+ "model.layers.50.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.50.self_attn.k_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.50.self_attn.k_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.50.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.50.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.50.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.50.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.50.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+ "model.layers.50.self_attn.q_proj.biases": "model-00005-of-00007.safetensors",
+ "model.layers.50.self_attn.q_proj.scales": "model-00005-of-00007.safetensors",
+ "model.layers.50.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.50.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.50.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.50.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.50.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.51.input_layernorm.weight": "model-00006-of-00007.safetensors",
+ "model.layers.51.mlp.down_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.51.mlp.down_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.51.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.51.mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.51.mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.51.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.51.mlp.up_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.51.mlp.up_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.51.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.51.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+ "model.layers.51.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.51.self_attn.k_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.51.self_attn.k_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.51.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.51.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.51.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.51.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.51.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.51.self_attn.q_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.51.self_attn.q_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.51.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.51.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.51.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.51.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.51.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.52.input_layernorm.weight": "model-00006-of-00007.safetensors",
+ "model.layers.52.mlp.down_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.52.mlp.down_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.52.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.52.mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.52.mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.52.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.52.mlp.up_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.52.mlp.up_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.52.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.52.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+ "model.layers.52.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.52.self_attn.k_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.52.self_attn.k_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.52.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.52.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.52.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.52.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.52.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.52.self_attn.q_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.52.self_attn.q_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.52.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.52.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.52.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.52.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.52.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.53.input_layernorm.weight": "model-00006-of-00007.safetensors",
+ "model.layers.53.mlp.down_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.53.mlp.down_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.53.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.53.mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.53.mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.53.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.53.mlp.up_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.53.mlp.up_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.53.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.53.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+ "model.layers.53.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.53.self_attn.k_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.53.self_attn.k_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.53.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.53.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.53.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.53.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.53.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.53.self_attn.q_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.53.self_attn.q_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.53.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.53.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.53.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.53.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.53.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.54.input_layernorm.weight": "model-00006-of-00007.safetensors",
+ "model.layers.54.mlp.down_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.54.mlp.down_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.54.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.54.mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.54.mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.54.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.54.mlp.up_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.54.mlp.up_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.54.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.54.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+ "model.layers.54.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.54.self_attn.k_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.54.self_attn.k_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.54.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.54.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.54.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.54.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.54.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.54.self_attn.q_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.54.self_attn.q_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.54.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.54.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.54.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.54.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.54.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.55.input_layernorm.weight": "model-00006-of-00007.safetensors",
+ "model.layers.55.mlp.down_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.55.mlp.down_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.55.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.55.mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.55.mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.55.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.55.mlp.up_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.55.mlp.up_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.55.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.55.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+ "model.layers.55.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.55.self_attn.k_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.55.self_attn.k_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.55.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.55.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.55.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.55.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.55.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.55.self_attn.q_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.55.self_attn.q_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.55.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.55.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.55.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.55.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.55.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.56.input_layernorm.weight": "model-00006-of-00007.safetensors",
+ "model.layers.56.mlp.down_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.56.mlp.down_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.56.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.56.mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.56.mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.56.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.56.mlp.up_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.56.mlp.up_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.56.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.56.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+ "model.layers.56.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.56.self_attn.k_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.56.self_attn.k_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.56.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.56.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.56.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.56.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.56.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.56.self_attn.q_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.56.self_attn.q_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.56.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.56.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.56.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.56.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.56.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.57.input_layernorm.weight": "model-00006-of-00007.safetensors",
+ "model.layers.57.mlp.down_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.57.mlp.down_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.57.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.57.mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.57.mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.57.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.57.mlp.up_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.57.mlp.up_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.57.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.57.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+ "model.layers.57.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.57.self_attn.k_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.57.self_attn.k_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.57.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.57.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.57.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.57.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.57.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.57.self_attn.q_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.57.self_attn.q_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.57.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.57.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.57.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.57.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.57.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.58.input_layernorm.weight": "model-00006-of-00007.safetensors",
+ "model.layers.58.mlp.down_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.58.mlp.down_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.58.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.58.mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.58.mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.58.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.58.mlp.up_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.58.mlp.up_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.58.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.58.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+ "model.layers.58.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.58.self_attn.k_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.58.self_attn.k_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.58.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.58.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.58.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.58.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.58.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.58.self_attn.q_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.58.self_attn.q_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.58.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.58.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.58.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.58.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.58.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.59.input_layernorm.weight": "model-00006-of-00007.safetensors",
+ "model.layers.59.mlp.down_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.59.mlp.down_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.59.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.59.mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.59.mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.59.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.59.mlp.up_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.59.mlp.up_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.59.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.59.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+ "model.layers.59.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.59.self_attn.k_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.59.self_attn.k_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.59.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.59.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.59.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.59.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.59.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.59.self_attn.q_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.59.self_attn.q_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.59.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.59.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.59.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.59.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.59.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors",
+ "model.layers.6.mlp.down_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.6.mlp.up_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+ "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+ "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+ "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.60.input_layernorm.weight": "model-00007-of-00007.safetensors",
+ "model.layers.60.mlp.down_proj.biases": "model-00007-of-00007.safetensors",
+ "model.layers.60.mlp.down_proj.scales": "model-00007-of-00007.safetensors",
+ "model.layers.60.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+ "model.layers.60.mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.60.mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.60.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.60.mlp.up_proj.biases": "model-00007-of-00007.safetensors",
+ "model.layers.60.mlp.up_proj.scales": "model-00007-of-00007.safetensors",
+ "model.layers.60.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+ "model.layers.60.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+ "model.layers.60.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.60.self_attn.k_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.60.self_attn.k_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.60.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.60.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.60.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.60.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.60.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.60.self_attn.q_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.60.self_attn.q_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.60.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.60.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+ "model.layers.60.self_attn.v_proj.biases": "model-00006-of-00007.safetensors",
+ "model.layers.60.self_attn.v_proj.scales": "model-00006-of-00007.safetensors",
+ "model.layers.60.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.61.input_layernorm.weight": "model-00007-of-00007.safetensors",
+ "model.layers.61.mlp.down_proj.biases": "model-00007-of-00007.safetensors",
+ "model.layers.61.mlp.down_proj.scales": "model-00007-of-00007.safetensors",
+ "model.layers.61.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+ "model.layers.61.mlp.gate_proj.biases": "model-00007-of-00007.safetensors",
+ "model.layers.61.mlp.gate_proj.scales": "model-00007-of-00007.safetensors",
+ "model.layers.61.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+ "model.layers.61.mlp.up_proj.biases": "model-00007-of-00007.safetensors",
+ "model.layers.61.mlp.up_proj.scales": "model-00007-of-00007.safetensors",
+ "model.layers.61.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+ "model.layers.61.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+ "model.layers.61.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+ "model.layers.61.self_attn.k_proj.biases": "model-00007-of-00007.safetensors",
+ "model.layers.61.self_attn.k_proj.scales": "model-00007-of-00007.safetensors",
+ "model.layers.61.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+ "model.layers.61.self_attn.o_proj.biases": "model-00007-of-00007.safetensors",
+ "model.layers.61.self_attn.o_proj.scales": "model-00007-of-00007.safetensors",
+ "model.layers.61.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+ "model.layers.61.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+ "model.layers.61.self_attn.q_proj.biases": "model-00007-of-00007.safetensors",
+ "model.layers.61.self_attn.q_proj.scales": "model-00007-of-00007.safetensors",
+ "model.layers.61.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+ "model.layers.61.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+ "model.layers.61.self_attn.v_proj.biases": "model-00007-of-00007.safetensors",
+ "model.layers.61.self_attn.v_proj.scales": "model-00007-of-00007.safetensors",
+ "model.layers.61.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+ "model.layers.62.input_layernorm.weight": "model-00007-of-00007.safetensors",
+ "model.layers.62.mlp.down_proj.biases": "model-00007-of-00007.safetensors",
+ "model.layers.62.mlp.down_proj.scales": "model-00007-of-00007.safetensors",
+ "model.layers.62.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+ "model.layers.62.mlp.gate_proj.biases": "model-00007-of-00007.safetensors",
+ "model.layers.62.mlp.gate_proj.scales": "model-00007-of-00007.safetensors",
+ "model.layers.62.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+ "model.layers.62.mlp.up_proj.biases": "model-00007-of-00007.safetensors",
+ "model.layers.62.mlp.up_proj.scales": "model-00007-of-00007.safetensors",
+ "model.layers.62.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+ "model.layers.62.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+ "model.layers.62.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+ "model.layers.62.self_attn.k_proj.biases": "model-00007-of-00007.safetensors",
+ "model.layers.62.self_attn.k_proj.scales": "model-00007-of-00007.safetensors",
+ "model.layers.62.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+ "model.layers.62.self_attn.o_proj.biases": "model-00007-of-00007.safetensors",
+ "model.layers.62.self_attn.o_proj.scales": "model-00007-of-00007.safetensors",
+ "model.layers.62.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+ "model.layers.62.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+ "model.layers.62.self_attn.q_proj.biases": "model-00007-of-00007.safetensors",
+ "model.layers.62.self_attn.q_proj.scales": "model-00007-of-00007.safetensors",
+ "model.layers.62.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+ "model.layers.62.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+ "model.layers.62.self_attn.v_proj.biases": "model-00007-of-00007.safetensors",
+ "model.layers.62.self_attn.v_proj.scales": "model-00007-of-00007.safetensors",
+ "model.layers.62.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+ "model.layers.63.input_layernorm.weight": "model-00007-of-00007.safetensors",
+ "model.layers.63.mlp.down_proj.biases": "model-00007-of-00007.safetensors",
+ "model.layers.63.mlp.down_proj.scales": "model-00007-of-00007.safetensors",
+ "model.layers.63.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+ "model.layers.63.mlp.gate_proj.biases": "model-00007-of-00007.safetensors",
+ "model.layers.63.mlp.gate_proj.scales": "model-00007-of-00007.safetensors",
+ "model.layers.63.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+ "model.layers.63.mlp.up_proj.biases": "model-00007-of-00007.safetensors",
+ "model.layers.63.mlp.up_proj.scales": "model-00007-of-00007.safetensors",
+ "model.layers.63.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+ "model.layers.63.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+ "model.layers.63.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+ "model.layers.63.self_attn.k_proj.biases": "model-00007-of-00007.safetensors",
+ "model.layers.63.self_attn.k_proj.scales": "model-00007-of-00007.safetensors",
+ "model.layers.63.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+ "model.layers.63.self_attn.o_proj.biases": "model-00007-of-00007.safetensors",
+ "model.layers.63.self_attn.o_proj.scales": "model-00007-of-00007.safetensors",
+ "model.layers.63.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+ "model.layers.63.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+ "model.layers.63.self_attn.q_proj.biases": "model-00007-of-00007.safetensors",
+ "model.layers.63.self_attn.q_proj.scales": "model-00007-of-00007.safetensors",
+ "model.layers.63.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+ "model.layers.63.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+ "model.layers.63.self_attn.v_proj.biases": "model-00007-of-00007.safetensors",
+ "model.layers.63.self_attn.v_proj.scales": "model-00007-of-00007.safetensors",
+ "model.layers.63.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors",
+ "model.layers.7.mlp.down_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.7.mlp.up_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+ "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+ "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+ "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.8.mlp.down_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.8.mlp.up_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.8.mlp.up_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+ "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+ "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+ "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00007.safetensors",
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00007.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.9.mlp.down_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.9.mlp.down_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.9.mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.9.mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.9.mlp.up_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.9.mlp.up_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.9.self_attn.k_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.9.self_attn.k_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.9.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.9.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.9.self_attn.q_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.9.self_attn.q_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+ "model.layers.9.self_attn.v_proj.biases": "model-00002-of-00007.safetensors",
+ "model.layers.9.self_attn.v_proj.scales": "model-00002-of-00007.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+ "model.norm.weight": "model-00007-of-00007.safetensors"
+ }
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B-8bit/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-8bit/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B-8bit/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-8bit/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B-8bit/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-8bit/tokenizer_config.json
@@ -0,0 +1,195 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/config.json b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e95cadc68ad8595dd9b2c7a5e90ab983db75aa35
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/config.json
@@ -0,0 +1,27 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 5120,
+ "initializer_range": 0.02,
+ "intermediate_size": 27648,
+ "max_position_embeddings": 131072,
+ "max_window_layers": 64,
+ "model_type": "qwen2",
+ "num_attention_heads": 40,
+ "num_hidden_layers": 64,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-05,
+ "rope_theta": 1000000.0,
+ "sliding_window": 131072,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.43.1",
+ "use_cache": true,
+ "use_sliding_window": false,
+ "vocab_size": 152064
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00001-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00001-of-00013.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..cb291f268a98a3bf438f004572ad43cfed1949c8
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00001-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:198a986faca9c4f83ed0cfa5d2a6f27aae2b1b76273bf4c70aa0ba413fa88c9a
+size 5174846610
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00002-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00002-of-00013.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d559ab89b5275a6db4e0324c9ceb96ce589ec222
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00002-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3018830b523669a3929ce7d34c6770378d9a32bb9a6ee766638f1c3a51952d7f
+size 5285039906
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00003-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00003-of-00013.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..43d690b00956623cc92e0533a95d2c0c13c53d3a
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00003-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44cb53fade96105c4f55842190214f3f4447df03def2296e4dc233f0babc53e0
+size 5159175031
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00004-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00004-of-00013.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0b9873a44e99face1a6f042e8381db966ab21d01
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00004-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:350e6c349b47522ee6c82234281174c21bc854e985465694513028923de76af3
+size 5159175052
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00005-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00005-of-00013.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..546c89cb9e1ee116eb814fd2eb93eff6c6bc04c3
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00005-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2acfe6a1fb188be45a6ee8dab9a1cd30b7f3f9ef60c9531a8eebf07596db125
+size 5285039984
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00006-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00006-of-00013.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1f49333506453d34206030d11324fbfee941acad
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00006-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8564bedae6b51193a30a2c8398a6af75d273a3bb813c5728d07a58dd1c0981d7
+size 5159175050
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00007-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00007-of-00013.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a50f390ba0b99594160644a73e9eb0f8500e7d59
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00007-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:537e7bd6301be85035aed58f6c8cf85fc04b4eac731225515a0d08cf009b07e5
+size 5159175054
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00008-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00008-of-00013.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..309a8c3beac7aec7455ed81f98d9a6496e765ed9
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00008-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30a31dbe307abc7c458e27309a72d225ff0314c28b962a6f3f2a073cb6c6bb37
+size 5285039984
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00009-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00009-of-00013.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a9276c8b5b7d1c73fff0253443090d55f9cee96a
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00009-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:598c30db75f25f27ff129e9ac102d96a77d4a34991329935fb4a3af06c9e02bb
+size 5159175048
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00010-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00010-of-00013.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d3ae61093d9496eca8e6d2a62f87b608658e4a78
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00010-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0387b0a7d79d4ff40cd11e123bf277e209f6efba35402fe3b46ea25cca317ce5
+size 5159175058
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00011-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00011-of-00013.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..815da2979308e9698217355a961853bf96b41cf9
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00011-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f45a13572fde4624fe66b1f0f65982727ba3e3205764027d3a083500b5b7ade6
+size 5285040002
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00012-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00012-of-00013.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..898045cc3551b9a7329cf64242a813903fcdc949
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00012-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0181957fb754d7e03c4c4efa9eedb3322c0cd31e3b7b8a174e44c41792869296
+size 5159175052
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00013-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00013-of-00013.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3d7c59167f95754a1985a32181e1874c1d452b2c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00013-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a67cd0a824cbb155e920d81d72d29ffa210be9d70bac91b335273431667168d
+size 3098609681
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..6b47c65cee2a02155e504beb592a01f9bfdec153
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model.safetensors.index.json
@@ -0,0 +1,778 @@
+{
+ "metadata": {
+ "total_size": 65527752704
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00013-of-00013.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00013.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00013.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00013.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00013.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00003-of-00013.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00013.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00004-of-00013.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00013.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00004-of-00013.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00004-of-00013.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00005-of-00013.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00013.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00005-of-00013.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00005-of-00013.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00005-of-00013.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00005-of-00013.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00005-of-00013.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00006-of-00013.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00006-of-00013.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00006-of-00013.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.28.input_layernorm.weight": "model-00006-of-00013.safetensors",
+ "model.layers.28.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.28.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+ "model.layers.28.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.28.self_attn.q_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.28.self_attn.v_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.29.input_layernorm.weight": "model-00006-of-00013.safetensors",
+ "model.layers.29.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.29.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+ "model.layers.29.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.29.self_attn.q_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.29.self_attn.v_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00013.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.30.input_layernorm.weight": "model-00007-of-00013.safetensors",
+ "model.layers.30.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.30.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+ "model.layers.30.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.30.self_attn.q_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.30.self_attn.v_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.31.input_layernorm.weight": "model-00007-of-00013.safetensors",
+ "model.layers.31.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.31.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+ "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.32.input_layernorm.weight": "model-00007-of-00013.safetensors",
+ "model.layers.32.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.32.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+ "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.32.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.32.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.33.input_layernorm.weight": "model-00007-of-00013.safetensors",
+ "model.layers.33.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.33.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+ "model.layers.33.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.33.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.33.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.34.input_layernorm.weight": "model-00007-of-00013.safetensors",
+ "model.layers.34.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.34.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+ "model.layers.34.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.34.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.34.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.35.input_layernorm.weight": "model-00008-of-00013.safetensors",
+ "model.layers.35.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.35.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+ "model.layers.35.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.35.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.35.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.36.input_layernorm.weight": "model-00008-of-00013.safetensors",
+ "model.layers.36.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.36.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+ "model.layers.36.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.36.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.36.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.37.input_layernorm.weight": "model-00008-of-00013.safetensors",
+ "model.layers.37.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.37.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+ "model.layers.37.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.37.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.37.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.38.input_layernorm.weight": "model-00008-of-00013.safetensors",
+ "model.layers.38.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.38.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+ "model.layers.38.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.38.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.38.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.39.input_layernorm.weight": "model-00008-of-00013.safetensors",
+ "model.layers.39.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.39.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.39.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+ "model.layers.39.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.39.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.39.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00013.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.40.input_layernorm.weight": "model-00008-of-00013.safetensors",
+ "model.layers.40.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.40.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.40.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.40.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+ "model.layers.40.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.40.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.40.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.40.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.40.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.40.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.40.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.41.input_layernorm.weight": "model-00009-of-00013.safetensors",
+ "model.layers.41.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.41.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+ "model.layers.41.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.41.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.41.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.42.input_layernorm.weight": "model-00009-of-00013.safetensors",
+ "model.layers.42.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.42.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+ "model.layers.42.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.42.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.42.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.43.input_layernorm.weight": "model-00009-of-00013.safetensors",
+ "model.layers.43.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.43.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.43.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+ "model.layers.43.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.43.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.43.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.44.input_layernorm.weight": "model-00009-of-00013.safetensors",
+ "model.layers.44.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.44.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.44.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.44.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+ "model.layers.44.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.44.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.44.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.44.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.44.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.44.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.44.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.45.input_layernorm.weight": "model-00009-of-00013.safetensors",
+ "model.layers.45.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.45.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.45.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.45.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+ "model.layers.45.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.45.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.45.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.45.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.45.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.45.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.45.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.46.input_layernorm.weight": "model-00010-of-00013.safetensors",
+ "model.layers.46.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.46.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.46.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+ "model.layers.46.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.46.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.46.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.46.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.46.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.46.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.46.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.47.input_layernorm.weight": "model-00010-of-00013.safetensors",
+ "model.layers.47.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.47.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+ "model.layers.47.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.47.self_attn.q_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.47.self_attn.v_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.48.input_layernorm.weight": "model-00010-of-00013.safetensors",
+ "model.layers.48.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.48.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.48.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+ "model.layers.48.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.48.self_attn.q_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.48.self_attn.v_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.49.input_layernorm.weight": "model-00010-of-00013.safetensors",
+ "model.layers.49.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.49.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.49.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.49.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+ "model.layers.49.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.49.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.49.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.49.self_attn.q_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.49.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.49.self_attn.v_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.49.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00013.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.50.input_layernorm.weight": "model-00010-of-00013.safetensors",
+ "model.layers.50.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.50.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.50.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.50.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+ "model.layers.50.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.50.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.50.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.50.self_attn.q_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.50.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.50.self_attn.v_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.50.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.51.input_layernorm.weight": "model-00011-of-00013.safetensors",
+ "model.layers.51.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.51.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.51.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+ "model.layers.51.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.51.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.51.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.51.self_attn.q_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.51.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.51.self_attn.v_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.51.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.52.input_layernorm.weight": "model-00011-of-00013.safetensors",
+ "model.layers.52.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.52.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+ "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.53.input_layernorm.weight": "model-00011-of-00013.safetensors",
+ "model.layers.53.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.53.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.53.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+ "model.layers.53.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.53.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.53.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.54.input_layernorm.weight": "model-00011-of-00013.safetensors",
+ "model.layers.54.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.54.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.54.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.54.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+ "model.layers.54.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.54.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.54.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.54.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.54.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.54.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.54.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.55.input_layernorm.weight": "model-00011-of-00013.safetensors",
+ "model.layers.55.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.55.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.55.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.55.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+ "model.layers.55.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.55.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.55.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.55.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.55.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.55.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.55.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.56.input_layernorm.weight": "model-00011-of-00013.safetensors",
+ "model.layers.56.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.56.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.56.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.56.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+ "model.layers.56.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.56.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.56.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.56.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.56.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.56.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.56.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.57.input_layernorm.weight": "model-00012-of-00013.safetensors",
+ "model.layers.57.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.57.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+ "model.layers.57.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.57.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.57.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.57.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.57.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.57.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.57.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.58.input_layernorm.weight": "model-00012-of-00013.safetensors",
+ "model.layers.58.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.58.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.58.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+ "model.layers.58.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.58.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.58.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.59.input_layernorm.weight": "model-00012-of-00013.safetensors",
+ "model.layers.59.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.59.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.59.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.59.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+ "model.layers.59.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.59.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.59.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.59.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.59.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.59.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.59.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00013.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.60.input_layernorm.weight": "model-00012-of-00013.safetensors",
+ "model.layers.60.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.60.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.60.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.60.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+ "model.layers.60.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.60.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.60.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.60.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.60.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.60.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.60.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.61.input_layernorm.weight": "model-00012-of-00013.safetensors",
+ "model.layers.61.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.61.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.61.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.61.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+ "model.layers.61.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.61.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.61.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.61.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.61.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.61.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.61.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.62.input_layernorm.weight": "model-00013-of-00013.safetensors",
+ "model.layers.62.mlp.down_proj.weight": "model-00013-of-00013.safetensors",
+ "model.layers.62.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.62.mlp.up_proj.weight": "model-00013-of-00013.safetensors",
+ "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00013.safetensors",
+ "model.layers.62.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.62.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.62.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.62.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.62.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.62.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.62.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.63.input_layernorm.weight": "model-00013-of-00013.safetensors",
+ "model.layers.63.mlp.down_proj.weight": "model-00013-of-00013.safetensors",
+ "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00013.safetensors",
+ "model.layers.63.mlp.up_proj.weight": "model-00013-of-00013.safetensors",
+ "model.layers.63.post_attention_layernorm.weight": "model-00013-of-00013.safetensors",
+ "model.layers.63.self_attn.k_proj.bias": "model-00013-of-00013.safetensors",
+ "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00013.safetensors",
+ "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00013.safetensors",
+ "model.layers.63.self_attn.q_proj.bias": "model-00013-of-00013.safetensors",
+ "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00013.safetensors",
+ "model.layers.63.self_attn.v_proj.bias": "model-00013-of-00013.safetensors",
+ "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00013.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00013.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00013.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00013.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+ "model.norm.weight": "model-00013-of-00013.safetensors"
+ }
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-bfloat16/tokenizer_config.json
@@ -0,0 +1,195 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/config.json b/DeepSeek-R1-Distill-Qwen-32B-float16/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e95cadc68ad8595dd9b2c7a5e90ab983db75aa35
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-float16/config.json
@@ -0,0 +1,27 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 5120,
+ "initializer_range": 0.02,
+ "intermediate_size": 27648,
+ "max_position_embeddings": 131072,
+ "max_window_layers": 64,
+ "model_type": "qwen2",
+ "num_attention_heads": 40,
+ "num_hidden_layers": 64,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-05,
+ "rope_theta": 1000000.0,
+ "sliding_window": 131072,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.43.1",
+ "use_cache": true,
+ "use_sliding_window": false,
+ "vocab_size": 152064
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00001-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00001-of-00013.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f9b3148217f6edfcf6a391ba995b3e52f50d403b
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00001-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afb60b214aeb4520856843c603633d95b689a51e4971ad96f35c9d2cdb42bf1c
+size 5174846564
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00002-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00002-of-00013.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f631c32ffe6f060c7f63793770bf6358c8056378
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00002-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:027fb274298705462adc75c960a642ffc9e57f7586964e27a90a86bc45e60448
+size 5285039836
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00003-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00003-of-00013.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..96c45e355e96e9246cb8d7228d2b9e03b635fc6c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00003-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:813f934d39fe60e38accf811cea82e8540ee22fb7e2635773b27214e483ae4fa
+size 5159174970
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00004-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00004-of-00013.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..dea4e3abacb4cd9b0f09f6b65d3b77bd1f7f840b
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00004-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c60fef930ed0ddcf916b4e69c2aae742359f559a5c07d8cdb5e0f0ad3514c39
+size 5159174991
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00005-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00005-of-00013.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4175cb52fe8f7c101a221a8188babf56b91077c3
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00005-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:228db8858bc8ec58a20c8f168d9bd3034de0ebd135752f41d8f035676f7a337d
+size 5285039914
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00006-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00006-of-00013.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..71757ae754ad2d3e6accaaa5f5770a75fe98f77b
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00006-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:606c8f7528115f78b318c4836f5ac17da26509c7bee422933a1ceee2621a20e8
+size 5159174989
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00007-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00007-of-00013.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7e6e77ad5d27f111880f93820572681d115287d8
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00007-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14a326ed0bd21631aeace8bfdb14f17c24b18e623fb3d0e5834be005c203e54d
+size 5159174993
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00008-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00008-of-00013.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..adf23b2da84529dfa8e0f5b3a7755520c18d9d2e
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00008-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:763a486bedfa701f0a2f290ee67da5e75c87ec8ca1a9816fc4b11f9e4b5d0741
+size 5285039914
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00009-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00009-of-00013.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..83f524ef62fa21a016cb6f708247ab15b8424819
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00009-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c14d13b82b1f32caef91d77ea2569d2c48093961837b5a36be1a8139444e3241
+size 5159174987
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00010-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00010-of-00013.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..9e285fc95b5f97f3abc326908eb810b527552dda
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00010-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f1ae29c430768d0fd4f24f9a6cfe9b05bac9c1f3a73f8303c8cafc55d57ad2f
+size 5159174997
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00011-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00011-of-00013.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..8aa8b7e80034b4c4d424012cd919ea9321dd459c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00011-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0661b1670ecb41c0f4b8851400745ea38c347b0e0de6735ef473e00e3116d811
+size 5285039932
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00012-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00012-of-00013.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3ef96b9f4e5a5371827f409412725275f8acc986
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00012-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07297b2d73eea88a5bd74f847fa705b236d5a1545f90b7917580a4debf582c81
+size 5159174991
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00013-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00013-of-00013.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..90456dc98939515c4c6dbd9b8c70a715bcd20521
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-float16/model-00013-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54a0b5e489b6ced01166836c08cfd5b90957ea540628ac9d4534b2d084b00c46
+size 3098609663
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B-float16/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..6b47c65cee2a02155e504beb592a01f9bfdec153
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-float16/model.safetensors.index.json
@@ -0,0 +1,778 @@
+{
+ "metadata": {
+ "total_size": 65527752704
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00013-of-00013.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00013.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00013.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00013.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00013.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00003-of-00013.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00013.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00004-of-00013.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00013.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00004-of-00013.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00004-of-00013.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00005-of-00013.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00004-of-00013.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00013.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00005-of-00013.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00005-of-00013.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00005-of-00013.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00005-of-00013.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00005-of-00013.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00006-of-00013.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00006-of-00013.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00006-of-00013.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.28.input_layernorm.weight": "model-00006-of-00013.safetensors",
+ "model.layers.28.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.28.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+ "model.layers.28.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.28.self_attn.q_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.28.self_attn.v_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.29.input_layernorm.weight": "model-00006-of-00013.safetensors",
+ "model.layers.29.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.29.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+ "model.layers.29.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.29.self_attn.q_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.29.self_attn.v_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00013.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+ "model.layers.30.input_layernorm.weight": "model-00007-of-00013.safetensors",
+ "model.layers.30.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.30.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+ "model.layers.30.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.30.self_attn.q_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.30.self_attn.v_proj.bias": "model-00006-of-00013.safetensors",
+ "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+ "model.layers.31.input_layernorm.weight": "model-00007-of-00013.safetensors",
+ "model.layers.31.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.31.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+ "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.32.input_layernorm.weight": "model-00007-of-00013.safetensors",
+ "model.layers.32.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.32.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+ "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.32.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.32.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.33.input_layernorm.weight": "model-00007-of-00013.safetensors",
+ "model.layers.33.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.33.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+ "model.layers.33.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.33.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.33.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.34.input_layernorm.weight": "model-00007-of-00013.safetensors",
+ "model.layers.34.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.34.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+ "model.layers.34.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.34.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.34.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.35.input_layernorm.weight": "model-00008-of-00013.safetensors",
+ "model.layers.35.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.35.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+ "model.layers.35.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.35.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.35.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
+ "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+ "model.layers.36.input_layernorm.weight": "model-00008-of-00013.safetensors",
+ "model.layers.36.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.36.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+ "model.layers.36.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.36.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.36.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.37.input_layernorm.weight": "model-00008-of-00013.safetensors",
+ "model.layers.37.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.37.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+ "model.layers.37.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.37.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.37.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.38.input_layernorm.weight": "model-00008-of-00013.safetensors",
+ "model.layers.38.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.38.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+ "model.layers.38.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.38.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.38.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.39.input_layernorm.weight": "model-00008-of-00013.safetensors",
+ "model.layers.39.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.39.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.39.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+ "model.layers.39.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.39.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.39.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00013.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.40.input_layernorm.weight": "model-00008-of-00013.safetensors",
+ "model.layers.40.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.40.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.40.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.40.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+ "model.layers.40.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.40.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.40.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.40.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.40.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.40.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.40.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.41.input_layernorm.weight": "model-00009-of-00013.safetensors",
+ "model.layers.41.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.41.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+ "model.layers.41.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.41.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.41.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
+ "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+ "model.layers.42.input_layernorm.weight": "model-00009-of-00013.safetensors",
+ "model.layers.42.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.42.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+ "model.layers.42.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.42.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.42.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.43.input_layernorm.weight": "model-00009-of-00013.safetensors",
+ "model.layers.43.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.43.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.43.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+ "model.layers.43.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.43.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.43.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.44.input_layernorm.weight": "model-00009-of-00013.safetensors",
+ "model.layers.44.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.44.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.44.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.44.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+ "model.layers.44.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.44.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.44.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.44.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.44.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.44.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.44.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.45.input_layernorm.weight": "model-00009-of-00013.safetensors",
+ "model.layers.45.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.45.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.45.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.45.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+ "model.layers.45.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.45.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.45.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.45.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.45.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.45.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.45.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.46.input_layernorm.weight": "model-00010-of-00013.safetensors",
+ "model.layers.46.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.46.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.46.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+ "model.layers.46.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.46.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.46.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.46.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.46.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.46.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
+ "model.layers.46.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+ "model.layers.47.input_layernorm.weight": "model-00010-of-00013.safetensors",
+ "model.layers.47.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.47.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+ "model.layers.47.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.47.self_attn.q_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.47.self_attn.v_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.48.input_layernorm.weight": "model-00010-of-00013.safetensors",
+ "model.layers.48.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.48.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.48.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+ "model.layers.48.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.48.self_attn.q_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.48.self_attn.v_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.49.input_layernorm.weight": "model-00010-of-00013.safetensors",
+ "model.layers.49.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.49.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.49.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.49.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+ "model.layers.49.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.49.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.49.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.49.self_attn.q_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.49.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.49.self_attn.v_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.49.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00013.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.50.input_layernorm.weight": "model-00010-of-00013.safetensors",
+ "model.layers.50.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.50.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.50.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.50.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+ "model.layers.50.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.50.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.50.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.50.self_attn.q_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.50.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.50.self_attn.v_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.50.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.51.input_layernorm.weight": "model-00011-of-00013.safetensors",
+ "model.layers.51.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.51.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.51.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+ "model.layers.51.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.51.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.51.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.51.self_attn.q_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.51.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.51.self_attn.v_proj.bias": "model-00010-of-00013.safetensors",
+ "model.layers.51.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+ "model.layers.52.input_layernorm.weight": "model-00011-of-00013.safetensors",
+ "model.layers.52.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.52.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+ "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.53.input_layernorm.weight": "model-00011-of-00013.safetensors",
+ "model.layers.53.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.53.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.53.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+ "model.layers.53.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.53.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.53.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.54.input_layernorm.weight": "model-00011-of-00013.safetensors",
+ "model.layers.54.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.54.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.54.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.54.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+ "model.layers.54.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.54.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.54.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.54.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.54.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.54.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.54.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.55.input_layernorm.weight": "model-00011-of-00013.safetensors",
+ "model.layers.55.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.55.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.55.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.55.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+ "model.layers.55.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.55.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.55.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.55.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.55.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.55.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.55.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.56.input_layernorm.weight": "model-00011-of-00013.safetensors",
+ "model.layers.56.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.56.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.56.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.56.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+ "model.layers.56.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.56.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.56.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.56.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.56.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.56.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.56.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.57.input_layernorm.weight": "model-00012-of-00013.safetensors",
+ "model.layers.57.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.57.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+ "model.layers.57.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.57.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.57.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.57.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.57.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.57.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
+ "model.layers.57.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+ "model.layers.58.input_layernorm.weight": "model-00012-of-00013.safetensors",
+ "model.layers.58.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.58.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.58.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+ "model.layers.58.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.58.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.58.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.59.input_layernorm.weight": "model-00012-of-00013.safetensors",
+ "model.layers.59.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.59.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.59.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.59.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+ "model.layers.59.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.59.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.59.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.59.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.59.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.59.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.59.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00013.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.60.input_layernorm.weight": "model-00012-of-00013.safetensors",
+ "model.layers.60.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.60.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.60.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.60.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+ "model.layers.60.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.60.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.60.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.60.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.60.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.60.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.60.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.61.input_layernorm.weight": "model-00012-of-00013.safetensors",
+ "model.layers.61.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.61.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.61.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.61.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+ "model.layers.61.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.61.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.61.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.61.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.61.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.61.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.61.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.62.input_layernorm.weight": "model-00013-of-00013.safetensors",
+ "model.layers.62.mlp.down_proj.weight": "model-00013-of-00013.safetensors",
+ "model.layers.62.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.62.mlp.up_proj.weight": "model-00013-of-00013.safetensors",
+ "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00013.safetensors",
+ "model.layers.62.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.62.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.62.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.62.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.62.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.62.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
+ "model.layers.62.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+ "model.layers.63.input_layernorm.weight": "model-00013-of-00013.safetensors",
+ "model.layers.63.mlp.down_proj.weight": "model-00013-of-00013.safetensors",
+ "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00013.safetensors",
+ "model.layers.63.mlp.up_proj.weight": "model-00013-of-00013.safetensors",
+ "model.layers.63.post_attention_layernorm.weight": "model-00013-of-00013.safetensors",
+ "model.layers.63.self_attn.k_proj.bias": "model-00013-of-00013.safetensors",
+ "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00013.safetensors",
+ "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00013.safetensors",
+ "model.layers.63.self_attn.q_proj.bias": "model-00013-of-00013.safetensors",
+ "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00013.safetensors",
+ "model.layers.63.self_attn.v_proj.bias": "model-00013-of-00013.safetensors",
+ "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00013.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00013.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00013.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00013.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+ "model.norm.weight": "model-00013-of-00013.safetensors"
+ }
+}
\ No newline at end of file
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B-float16/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-float16/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B-float16/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-float16/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B-float16/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd
--- /dev/null
+++ b/DeepSeek-R1-Distill-Qwen-32B-float16/tokenizer_config.json
@@ -0,0 +1,195 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/README.md b/README.md
index c5a73cc97e0b7f963ae28864ffdc177c996fdee1..8c87f6c865632c1f3eb5107c43f927f3934303a8 100644
--- a/README.md
+++ b/README.md
@@ -1,7 +1,6 @@
---
quantized_by: sealad886
-license_link: >-
- https://huggingface.co./deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/blob/main/LICENSE
+license_link: https://huggingface.co./deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/blob/main/LICENSE
language:
- en
pipeline_tag: text-generation
@@ -9,7 +8,7 @@ base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
tags:
- chat
- mlx
-license: mit
+- conversations
---
# mlx-community/DeepSeek-R1-Distill-Qwen-32B
@@ -43,7 +42,6 @@ The model conversion uses a range of quantization configurations defined via `ml
Converts the model to a different floating point precision without quantizing weights.
- **bfloat16:** Model converted to bfloat16 precision.
- **float16:** Model converted to float16 precision.
- - **float32:** Model converted to float32 precision.
## Use with mlx