Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
+  "architectures": [
+    "Qwen2MoeForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "decoder_sparse_step": 1,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "mlp_only_layers": [],
+  "model_type": "qwen2_moe",
+  "moe_intermediate_size": 18944,
+  "norm_topk_prob": true,
+  "num_attention_heads": 28,
+  "num_experts": 2,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "router_aux_loss_coef": 0.001,
+  "shared_expert_intermediate_size": 18944,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

mergekit_moe_config.yml

@@ -0,0 +1,13 @@
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+gate_mode: random
+dtype: float16
+tokenizer_source: "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B"
+experts_per_token: 2
+experts:
+  - source_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+  - source_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+shared_experts:
+  - source_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+    positive_prompts:
+      - ""
+    residual_scale: 0.1

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abc7a43358fe1f176652b233fa0e54ffe85724cc6be80186a91e2370796a025b
+size 4914261592

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a614606522ae3ac2d6d1d66dc330c398206bb658a7761a594aa76f23a88d2598
+size 4943640232

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ec8a0b9d490e4d3790046b984815b82a01e7384748643761f72a73b27964d49
+size 4916115056

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6de334a41ba833ec6fea9aa05a4ec1b65be1f144fade075d07b43fe5706dd48
+size 4943640328

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfd822a6f7576051d0168c997f67c1c19b9ae952f6d38af70bbbcec516eeb93a
+size 4916115080

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b826f65cd5d91fcf5e50927d33c8e643846dec4a06331df49873a0ba03d04815
+size 4316649408

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.1", "total_size": 28950354944}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00006.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.experts.0.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.experts.1.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.shared_expert.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.experts.0.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.experts.1.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.shared_expert.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.experts.0.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.experts.1.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.shared_expert.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.weight": "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.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.weight": "model-00001-of-00006.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.experts.0.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.experts.1.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.shared_expert.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.shared_expert.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.experts.0.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.experts.1.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.shared_expert.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.weight": "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.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.weight": "model-00001-of-00006.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.2.mlp.experts.0.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.mlp.experts.1.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.mlp.shared_expert.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.mlp.shared_expert.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.mlp.experts.0.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.mlp.experts.1.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.mlp.shared_expert.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.weight": "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.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.weight": "model-00001-of-00006.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.3.mlp.experts.0.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.mlp.experts.1.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.mlp.shared_expert.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.mlp.shared_expert.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.mlp.experts.0.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.mlp.experts.1.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.mlp.shared_expert.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.weight": "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.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.weight": "model-00001-of-00006.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.4.mlp.experts.0.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.4.mlp.experts.1.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.4.mlp.shared_expert.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.4.mlp.shared_expert.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.4.mlp.experts.0.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.4.mlp.experts.1.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.4.mlp.shared_expert.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.5.mlp.experts.0.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.5.mlp.experts.1.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.5.mlp.shared_expert.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.5.mlp.shared_expert.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.5.mlp.experts.0.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.5.mlp.experts.1.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.5.mlp.shared_expert.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.6.mlp.experts.0.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.mlp.experts.1.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.mlp.shared_expert.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.mlp.shared_expert.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.mlp.experts.0.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.mlp.experts.1.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.mlp.shared_expert.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.7.mlp.experts.0.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.mlp.experts.1.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.mlp.shared_expert.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.mlp.shared_expert.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.mlp.experts.0.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.mlp.experts.1.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.mlp.shared_expert.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.8.mlp.experts.0.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.mlp.experts.1.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.mlp.shared_expert.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.mlp.shared_expert.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.mlp.experts.0.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.mlp.experts.1.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.mlp.shared_expert.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.9.mlp.experts.0.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.9.mlp.experts.1.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.9.mlp.shared_expert.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.9.mlp.shared_expert.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.9.mlp.experts.0.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.9.mlp.experts.1.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.9.mlp.shared_expert.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.10.mlp.experts.0.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.10.mlp.experts.1.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.10.mlp.shared_expert.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.10.mlp.shared_expert.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.10.mlp.experts.0.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.10.mlp.experts.1.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.10.mlp.shared_expert.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.11.mlp.experts.0.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.mlp.experts.1.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.mlp.shared_expert.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.mlp.shared_expert.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.mlp.experts.0.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.mlp.experts.1.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.mlp.shared_expert.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.12.mlp.experts.0.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.mlp.experts.1.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.mlp.shared_expert.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.mlp.shared_expert.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.mlp.experts.0.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.mlp.experts.1.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.mlp.shared_expert.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.13.mlp.experts.0.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.mlp.experts.1.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.mlp.shared_expert.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.mlp.shared_expert.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.mlp.experts.0.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.mlp.experts.1.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.mlp.shared_expert.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.14.mlp.experts.0.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.mlp.experts.1.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.mlp.shared_expert.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.14.mlp.shared_expert.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.14.mlp.experts.0.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.14.mlp.experts.1.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.14.mlp.shared_expert.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.15.mlp.experts.0.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.15.mlp.experts.1.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.15.mlp.shared_expert.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.15.mlp.shared_expert.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.15.mlp.experts.0.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.15.mlp.experts.1.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.15.mlp.shared_expert.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.16.mlp.experts.0.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.16.mlp.experts.1.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.16.mlp.shared_expert.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.16.mlp.shared_expert.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.16.mlp.experts.0.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.16.mlp.experts.1.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.16.mlp.shared_expert.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.17.mlp.experts.0.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.17.mlp.experts.1.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.17.mlp.shared_expert.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.17.mlp.shared_expert.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.17.mlp.experts.0.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.17.mlp.experts.1.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.17.mlp.shared_expert.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.18.mlp.experts.0.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.18.mlp.experts.1.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.18.mlp.shared_expert.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.18.mlp.shared_expert.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.18.mlp.experts.0.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.18.mlp.experts.1.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.18.mlp.shared_expert.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.19.mlp.experts.0.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.19.mlp.experts.1.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.19.mlp.shared_expert.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.19.mlp.shared_expert.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.19.mlp.experts.0.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.19.mlp.experts.1.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.19.mlp.shared_expert.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.20.mlp.experts.0.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.20.mlp.experts.1.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.20.mlp.shared_expert.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.20.mlp.shared_expert.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.20.mlp.experts.0.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.20.mlp.experts.1.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.20.mlp.shared_expert.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.21.mlp.experts.0.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.21.mlp.experts.1.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.21.mlp.shared_expert.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.21.mlp.shared_expert.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.21.mlp.experts.0.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.21.mlp.experts.1.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.21.mlp.shared_expert.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.22.mlp.experts.0.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.22.mlp.experts.1.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.22.mlp.shared_expert.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.22.mlp.shared_expert.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.22.mlp.experts.0.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.22.mlp.experts.1.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.22.mlp.shared_expert.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.23.mlp.experts.0.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.mlp.experts.1.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.mlp.shared_expert.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.mlp.shared_expert.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.mlp.experts.0.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.mlp.experts.1.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.mlp.shared_expert.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.24.mlp.experts.0.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.24.mlp.experts.1.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.24.mlp.shared_expert.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.24.mlp.shared_expert.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.24.mlp.experts.0.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.24.mlp.experts.1.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.24.mlp.shared_expert.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.25.mlp.experts.0.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.25.mlp.experts.1.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.25.mlp.shared_expert.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.25.mlp.shared_expert.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.25.mlp.experts.0.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.25.mlp.experts.1.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.25.mlp.shared_expert.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.26.mlp.experts.0.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.26.mlp.experts.1.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.26.mlp.shared_expert.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.26.mlp.shared_expert.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.26.mlp.experts.0.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.26.mlp.experts.1.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.26.mlp.shared_expert.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.27.mlp.experts.0.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.27.mlp.experts.1.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.27.mlp.shared_expert.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.27.mlp.experts.0.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.27.mlp.experts.1.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.27.mlp.shared_expert.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.27.mlp.experts.0.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.27.mlp.experts.1.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.27.mlp.shared_expert.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.norm.weight": "model-00006-of-00006.safetensors", "lm_head.weight": "model-00006-of-00006.safetensors", "model.layers.0.mlp.gate.weight": "model-00006-of-00006.safetensors", "model.layers.0.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", "model.layers.1.mlp.gate.weight": "model-00006-of-00006.safetensors", "model.layers.1.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", "model.layers.2.mlp.gate.weight": "model-00006-of-00006.safetensors", "model.layers.2.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", "model.layers.3.mlp.gate.weight": "model-00006-of-00006.safetensors", "model.layers.3.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", "model.layers.4.mlp.gate.weight": "model-00006-of-00006.safetensors", "model.layers.4.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", "model.layers.5.mlp.gate.weight": "model-00006-of-00006.safetensors", "model.layers.5.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", "model.layers.6.mlp.gate.weight": "model-00006-of-00006.safetensors", "model.layers.6.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", "model.layers.7.mlp.gate.weight": "model-00006-of-00006.safetensors", "model.layers.7.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", "model.layers.8.mlp.gate.weight": "model-00006-of-00006.safetensors", "model.layers.8.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", "model.layers.9.mlp.gate.weight": "model-00006-of-00006.safetensors", "model.layers.9.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", "model.layers.10.mlp.gate.weight": "model-00006-of-00006.safetensors", "model.layers.10.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", "model.layers.11.mlp.gate.weight": "model-00006-of-00006.safetensors", "model.layers.11.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", "model.layers.12.mlp.gate.weight": "model-00006-of-00006.safetensors", "model.layers.12.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", "model.layers.13.mlp.gate.weight": "model-00006-of-00006.safetensors", "model.layers.13.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", "model.layers.14.mlp.gate.weight": "model-00006-of-00006.safetensors", "model.layers.14.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", "model.layers.15.mlp.gate.weight": "model-00006-of-00006.safetensors", "model.layers.15.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", "model.layers.16.mlp.gate.weight": "model-00006-of-00006.safetensors", "model.layers.16.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", "model.layers.17.mlp.gate.weight": "model-00006-of-00006.safetensors", "model.layers.17.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", "model.layers.18.mlp.gate.weight": "model-00006-of-00006.safetensors", "model.layers.18.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", "model.layers.19.mlp.gate.weight": "model-00006-of-00006.safetensors", "model.layers.19.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", "model.layers.20.mlp.gate.weight": "model-00006-of-00006.safetensors", "model.layers.20.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", "model.layers.21.mlp.gate.weight": "model-00006-of-00006.safetensors", "model.layers.21.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", "model.layers.22.mlp.gate.weight": "model-00006-of-00006.safetensors", "model.layers.22.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", "model.layers.23.mlp.gate.weight": "model-00006-of-00006.safetensors", "model.layers.23.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", "model.layers.24.mlp.gate.weight": "model-00006-of-00006.safetensors", "model.layers.24.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", "model.layers.25.mlp.gate.weight": "model-00006-of-00006.safetensors", "model.layers.25.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", "model.layers.26.mlp.gate.weight": "model-00006-of-00006.safetensors", "model.layers.26.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", "model.layers.27.mlp.gate.weight": "model-00006-of-00006.safetensors", "model.layers.27.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "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": "<｜begin▁of▁sentence｜>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778

tokenizer_config.json

@@ -0,0 +1,194 @@
+{
+  "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": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "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": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "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 '</think>' in content %}{% set content = content.split('</think>')[-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｜>'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜begin▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}