Upload ChatGLMForConditionalGeneration

config.json

@@ -10,8 +10,8 @@
   "attention_dropout": 0.0,
   "attention_softmax_in_fp32": true,
   "auto_map": {
-    "AutoConfig": "THUDM/glm-4-9b--configuration_chatglm.ChatGLMConfig",
-    "AutoModel": "THUDM/glm-4-9b--modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoConfig": "configuration_chatglm.ChatGLMConfig",
+    "AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
     "AutoModelForCausalLM": "THUDM/glm-4-9b--modeling_chatglm.ChatGLMForConditionalGeneration",
     "AutoModelForSeq2SeqLM": "THUDM/glm-4-9b--modeling_chatglm.ChatGLMForConditionalGeneration",
     "AutoModelForSequenceClassification": "THUDM/glm-4-9b--modeling_chatglm.ChatGLMForSequenceClassification"
@@ -43,7 +43,7 @@
   "seq_length": 8192,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.41.2",
+  "transformers_version": "4.42.3",
   "use_cache": true,
   "vocab_size": 151552
 }

generation_config.json

@@ -9,5 +9,5 @@
   "pad_token_id": 151329,
   "temperature": 0.8,
   "top_p": 0.8,
-  "transformers_version": "4.41.2"
+  "transformers_version": "4.42.3"
 }

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab965e863a4ea718c0ab3f3b35aa2fbb858aa7aef7af4bff04f7d9f5381f704b
+size 2944534184

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40dc05576fda8c25408e31f50f105e9c74f8621736f5120ddb84b84ca064d57e
+size 2855458256

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0424b4f641aea70e233280ade2fed652f9d5787b36924b56f3dd9a965166f632
+size 2855458312

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4794a907790cbfbd60028eca5e58fb70480c112533b6233084ef260a3429480
+size 2855458312

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2d96111fbdff247302ecde0c226c759dee1d004b52eafee2826975d4da1cfad
+size 2855458312

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6040e7612cddaad2901fa88d8511473aef12482697170db729d7fbd6ae6903ed
+size 2855458312

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9224222d9d418762261a933241fe9adcd952cd0f9f7e677ce6d8aaf0222f78e4
+size 1578115584

model.safetensors.index.json

@@ -3,289 +3,289 @@
     "total_size": 18799902784
   },
   "weight_map": {
-    "transformer.embedding.word_embeddings.weight": "model-00001-of-00022.safetensors",
-    "transformer.encoder.final_layernorm.weight": "model-00021-of-00022.safetensors",
-    "transformer.encoder.layers.0.input_layernorm.weight": "model-00002-of-00022.safetensors",
-    "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "model-00002-of-00022.safetensors",
-    "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "model-00002-of-00022.safetensors",
-    "transformer.encoder.layers.0.post_attention_layernorm.weight": "model-00002-of-00022.safetensors",
-    "transformer.encoder.layers.0.self_attention.dense.weight": "model-00002-of-00022.safetensors",
-    "transformer.encoder.layers.0.self_attention.query_key_value.bias": "model-00002-of-00022.safetensors",
-    "transformer.encoder.layers.0.self_attention.query_key_value.weight": "model-00002-of-00022.safetensors",
-    "transformer.encoder.layers.1.input_layernorm.weight": "model-00002-of-00022.safetensors",
-    "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "model-00002-of-00022.safetensors",
-    "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "model-00002-of-00022.safetensors",
-    "transformer.encoder.layers.1.post_attention_layernorm.weight": "model-00002-of-00022.safetensors",
-    "transformer.encoder.layers.1.self_attention.dense.weight": "model-00002-of-00022.safetensors",
-    "transformer.encoder.layers.1.self_attention.query_key_value.bias": "model-00002-of-00022.safetensors",
-    "transformer.encoder.layers.1.self_attention.query_key_value.weight": "model-00002-of-00022.safetensors",
-    "transformer.encoder.layers.10.input_layernorm.weight": "model-00006-of-00022.safetensors",
-    "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "model-00007-of-00022.safetensors",
-    "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "model-00007-of-00022.safetensors",
-    "transformer.encoder.layers.10.post_attention_layernorm.weight": "model-00006-of-00022.safetensors",
-    "transformer.encoder.layers.10.self_attention.dense.weight": "model-00006-of-00022.safetensors",
-    "transformer.encoder.layers.10.self_attention.query_key_value.bias": "model-00006-of-00022.safetensors",
-    "transformer.encoder.layers.10.self_attention.query_key_value.weight": "model-00006-of-00022.safetensors",
-    "transformer.encoder.layers.11.input_layernorm.weight": "model-00007-of-00022.safetensors",
-    "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "model-00007-of-00022.safetensors",
-    "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "model-00007-of-00022.safetensors",
-    "transformer.encoder.layers.11.post_attention_layernorm.weight": "model-00007-of-00022.safetensors",
-    "transformer.encoder.layers.11.self_attention.dense.weight": "model-00007-of-00022.safetensors",
-    "transformer.encoder.layers.11.self_attention.query_key_value.bias": "model-00007-of-00022.safetensors",
-    "transformer.encoder.layers.11.self_attention.query_key_value.weight": "model-00007-of-00022.safetensors",
-    "transformer.encoder.layers.12.input_layernorm.weight": "model-00007-of-00022.safetensors",
-    "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "model-00008-of-00022.safetensors",
-    "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "model-00008-of-00022.safetensors",
-    "transformer.encoder.layers.12.post_attention_layernorm.weight": "model-00007-of-00022.safetensors",
-    "transformer.encoder.layers.12.self_attention.dense.weight": "model-00007-of-00022.safetensors",
-    "transformer.encoder.layers.12.self_attention.query_key_value.bias": "model-00007-of-00022.safetensors",
-    "transformer.encoder.layers.12.self_attention.query_key_value.weight": "model-00007-of-00022.safetensors",
-    "transformer.encoder.layers.13.input_layernorm.weight": "model-00008-of-00022.safetensors",
-    "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "model-00008-of-00022.safetensors",
-    "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "model-00008-of-00022.safetensors",
-    "transformer.encoder.layers.13.post_attention_layernorm.weight": "model-00008-of-00022.safetensors",
-    "transformer.encoder.layers.13.self_attention.dense.weight": "model-00008-of-00022.safetensors",
-    "transformer.encoder.layers.13.self_attention.query_key_value.bias": "model-00008-of-00022.safetensors",
-    "transformer.encoder.layers.13.self_attention.query_key_value.weight": "model-00008-of-00022.safetensors",
-    "transformer.encoder.layers.14.input_layernorm.weight": "model-00008-of-00022.safetensors",
-    "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "model-00009-of-00022.safetensors",
-    "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "model-00009-of-00022.safetensors",
-    "transformer.encoder.layers.14.post_attention_layernorm.weight": "model-00008-of-00022.safetensors",
-    "transformer.encoder.layers.14.self_attention.dense.weight": "model-00008-of-00022.safetensors",
-    "transformer.encoder.layers.14.self_attention.query_key_value.bias": "model-00008-of-00022.safetensors",
-    "transformer.encoder.layers.14.self_attention.query_key_value.weight": "model-00008-of-00022.safetensors",
-    "transformer.encoder.layers.15.input_layernorm.weight": "model-00009-of-00022.safetensors",
-    "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "model-00009-of-00022.safetensors",
-    "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "model-00009-of-00022.safetensors",
-    "transformer.encoder.layers.15.post_attention_layernorm.weight": "model-00009-of-00022.safetensors",
-    "transformer.encoder.layers.15.self_attention.dense.weight": "model-00009-of-00022.safetensors",
-    "transformer.encoder.layers.15.self_attention.query_key_value.bias": "model-00009-of-00022.safetensors",
-    "transformer.encoder.layers.15.self_attention.query_key_value.weight": "model-00009-of-00022.safetensors",
-    "transformer.encoder.layers.16.input_layernorm.weight": "model-00009-of-00022.safetensors",
-    "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "model-00010-of-00022.safetensors",
-    "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "model-00010-of-00022.safetensors",
-    "transformer.encoder.layers.16.post_attention_layernorm.weight": "model-00009-of-00022.safetensors",
-    "transformer.encoder.layers.16.self_attention.dense.weight": "model-00009-of-00022.safetensors",
-    "transformer.encoder.layers.16.self_attention.query_key_value.bias": "model-00009-of-00022.safetensors",
-    "transformer.encoder.layers.16.self_attention.query_key_value.weight": "model-00009-of-00022.safetensors",
-    "transformer.encoder.layers.17.input_layernorm.weight": "model-00010-of-00022.safetensors",
-    "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "model-00010-of-00022.safetensors",
-    "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "model-00010-of-00022.safetensors",
-    "transformer.encoder.layers.17.post_attention_layernorm.weight": "model-00010-of-00022.safetensors",
-    "transformer.encoder.layers.17.self_attention.dense.weight": "model-00010-of-00022.safetensors",
-    "transformer.encoder.layers.17.self_attention.query_key_value.bias": "model-00010-of-00022.safetensors",
-    "transformer.encoder.layers.17.self_attention.query_key_value.weight": "model-00010-of-00022.safetensors",
-    "transformer.encoder.layers.18.input_layernorm.weight": "model-00010-of-00022.safetensors",
-    "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "model-00011-of-00022.safetensors",
-    "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "model-00011-of-00022.safetensors",
-    "transformer.encoder.layers.18.post_attention_layernorm.weight": "model-00010-of-00022.safetensors",
-    "transformer.encoder.layers.18.self_attention.dense.weight": "model-00010-of-00022.safetensors",
-    "transformer.encoder.layers.18.self_attention.query_key_value.bias": "model-00010-of-00022.safetensors",
-    "transformer.encoder.layers.18.self_attention.query_key_value.weight": "model-00010-of-00022.safetensors",
-    "transformer.encoder.layers.19.input_layernorm.weight": "model-00011-of-00022.safetensors",
-    "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "model-00011-of-00022.safetensors",
-    "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "model-00011-of-00022.safetensors",
-    "transformer.encoder.layers.19.post_attention_layernorm.weight": "model-00011-of-00022.safetensors",
-    "transformer.encoder.layers.19.self_attention.dense.weight": "model-00011-of-00022.safetensors",
-    "transformer.encoder.layers.19.self_attention.query_key_value.bias": "model-00011-of-00022.safetensors",
-    "transformer.encoder.layers.19.self_attention.query_key_value.weight": "model-00011-of-00022.safetensors",
-    "transformer.encoder.layers.2.input_layernorm.weight": "model-00002-of-00022.safetensors",
-    "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "model-00003-of-00022.safetensors",
-    "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "model-00003-of-00022.safetensors",
-    "transformer.encoder.layers.2.post_attention_layernorm.weight": "model-00002-of-00022.safetensors",
-    "transformer.encoder.layers.2.self_attention.dense.weight": "model-00002-of-00022.safetensors",
-    "transformer.encoder.layers.2.self_attention.query_key_value.bias": "model-00002-of-00022.safetensors",
-    "transformer.encoder.layers.2.self_attention.query_key_value.weight": "model-00002-of-00022.safetensors",
-    "transformer.encoder.layers.20.input_layernorm.weight": "model-00011-of-00022.safetensors",
-    "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "model-00012-of-00022.safetensors",
-    "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "model-00012-of-00022.safetensors",
-    "transformer.encoder.layers.20.post_attention_layernorm.weight": "model-00011-of-00022.safetensors",
-    "transformer.encoder.layers.20.self_attention.dense.weight": "model-00011-of-00022.safetensors",
-    "transformer.encoder.layers.20.self_attention.query_key_value.bias": "model-00011-of-00022.safetensors",
-    "transformer.encoder.layers.20.self_attention.query_key_value.weight": "model-00011-of-00022.safetensors",
-    "transformer.encoder.layers.21.input_layernorm.weight": "model-00012-of-00022.safetensors",
-    "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "model-00012-of-00022.safetensors",
-    "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "model-00012-of-00022.safetensors",
-    "transformer.encoder.layers.21.post_attention_layernorm.weight": "model-00012-of-00022.safetensors",
-    "transformer.encoder.layers.21.self_attention.dense.weight": "model-00012-of-00022.safetensors",
-    "transformer.encoder.layers.21.self_attention.query_key_value.bias": "model-00012-of-00022.safetensors",
-    "transformer.encoder.layers.21.self_attention.query_key_value.weight": "model-00012-of-00022.safetensors",
-    "transformer.encoder.layers.22.input_layernorm.weight": "model-00012-of-00022.safetensors",
-    "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "model-00013-of-00022.safetensors",
-    "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "model-00013-of-00022.safetensors",
-    "transformer.encoder.layers.22.post_attention_layernorm.weight": "model-00012-of-00022.safetensors",
-    "transformer.encoder.layers.22.self_attention.dense.weight": "model-00012-of-00022.safetensors",
-    "transformer.encoder.layers.22.self_attention.query_key_value.bias": "model-00012-of-00022.safetensors",
-    "transformer.encoder.layers.22.self_attention.query_key_value.weight": "model-00012-of-00022.safetensors",
-    "transformer.encoder.layers.23.input_layernorm.weight": "model-00013-of-00022.safetensors",
-    "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "model-00013-of-00022.safetensors",
-    "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "model-00013-of-00022.safetensors",
-    "transformer.encoder.layers.23.post_attention_layernorm.weight": "model-00013-of-00022.safetensors",
-    "transformer.encoder.layers.23.self_attention.dense.weight": "model-00013-of-00022.safetensors",
-    "transformer.encoder.layers.23.self_attention.query_key_value.bias": "model-00013-of-00022.safetensors",
-    "transformer.encoder.layers.23.self_attention.query_key_value.weight": "model-00013-of-00022.safetensors",
-    "transformer.encoder.layers.24.input_layernorm.weight": "model-00013-of-00022.safetensors",
-    "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "model-00014-of-00022.safetensors",
-    "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "model-00014-of-00022.safetensors",
-    "transformer.encoder.layers.24.post_attention_layernorm.weight": "model-00013-of-00022.safetensors",
-    "transformer.encoder.layers.24.self_attention.dense.weight": "model-00013-of-00022.safetensors",
-    "transformer.encoder.layers.24.self_attention.query_key_value.bias": "model-00013-of-00022.safetensors",
-    "transformer.encoder.layers.24.self_attention.query_key_value.weight": "model-00013-of-00022.safetensors",
-    "transformer.encoder.layers.25.input_layernorm.weight": "model-00014-of-00022.safetensors",
-    "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "model-00014-of-00022.safetensors",
-    "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "model-00014-of-00022.safetensors",
-    "transformer.encoder.layers.25.post_attention_layernorm.weight": "model-00014-of-00022.safetensors",
-    "transformer.encoder.layers.25.self_attention.dense.weight": "model-00014-of-00022.safetensors",
-    "transformer.encoder.layers.25.self_attention.query_key_value.bias": "model-00014-of-00022.safetensors",
-    "transformer.encoder.layers.25.self_attention.query_key_value.weight": "model-00014-of-00022.safetensors",
-    "transformer.encoder.layers.26.input_layernorm.weight": "model-00014-of-00022.safetensors",
-    "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "model-00015-of-00022.safetensors",
-    "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "model-00015-of-00022.safetensors",
-    "transformer.encoder.layers.26.post_attention_layernorm.weight": "model-00014-of-00022.safetensors",
-    "transformer.encoder.layers.26.self_attention.dense.weight": "model-00014-of-00022.safetensors",
-    "transformer.encoder.layers.26.self_attention.query_key_value.bias": "model-00014-of-00022.safetensors",
-    "transformer.encoder.layers.26.self_attention.query_key_value.weight": "model-00014-of-00022.safetensors",
-    "transformer.encoder.layers.27.input_layernorm.weight": "model-00015-of-00022.safetensors",
-    "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "model-00015-of-00022.safetensors",
-    "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "model-00015-of-00022.safetensors",
-    "transformer.encoder.layers.27.post_attention_layernorm.weight": "model-00015-of-00022.safetensors",
-    "transformer.encoder.layers.27.self_attention.dense.weight": "model-00015-of-00022.safetensors",
-    "transformer.encoder.layers.27.self_attention.query_key_value.bias": "model-00015-of-00022.safetensors",
-    "transformer.encoder.layers.27.self_attention.query_key_value.weight": "model-00015-of-00022.safetensors",
-    "transformer.encoder.layers.28.input_layernorm.weight": "model-00015-of-00022.safetensors",
-    "transformer.encoder.layers.28.mlp.dense_4h_to_h.weight": "model-00016-of-00022.safetensors",
-    "transformer.encoder.layers.28.mlp.dense_h_to_4h.weight": "model-00016-of-00022.safetensors",
-    "transformer.encoder.layers.28.post_attention_layernorm.weight": "model-00015-of-00022.safetensors",
-    "transformer.encoder.layers.28.self_attention.dense.weight": "model-00015-of-00022.safetensors",
-    "transformer.encoder.layers.28.self_attention.query_key_value.bias": "model-00015-of-00022.safetensors",
-    "transformer.encoder.layers.28.self_attention.query_key_value.weight": "model-00015-of-00022.safetensors",
-    "transformer.encoder.layers.29.input_layernorm.weight": "model-00016-of-00022.safetensors",
-    "transformer.encoder.layers.29.mlp.dense_4h_to_h.weight": "model-00016-of-00022.safetensors",
-    "transformer.encoder.layers.29.mlp.dense_h_to_4h.weight": "model-00016-of-00022.safetensors",
-    "transformer.encoder.layers.29.post_attention_layernorm.weight": "model-00016-of-00022.safetensors",
-    "transformer.encoder.layers.29.self_attention.dense.weight": "model-00016-of-00022.safetensors",
-    "transformer.encoder.layers.29.self_attention.query_key_value.bias": "model-00016-of-00022.safetensors",
-    "transformer.encoder.layers.29.self_attention.query_key_value.weight": "model-00016-of-00022.safetensors",
-    "transformer.encoder.layers.3.input_layernorm.weight": "model-00003-of-00022.safetensors",
-    "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "model-00003-of-00022.safetensors",
-    "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "model-00003-of-00022.safetensors",
-    "transformer.encoder.layers.3.post_attention_layernorm.weight": "model-00003-of-00022.safetensors",
-    "transformer.encoder.layers.3.self_attention.dense.weight": "model-00003-of-00022.safetensors",
-    "transformer.encoder.layers.3.self_attention.query_key_value.bias": "model-00003-of-00022.safetensors",
-    "transformer.encoder.layers.3.self_attention.query_key_value.weight": "model-00003-of-00022.safetensors",
-    "transformer.encoder.layers.30.input_layernorm.weight": "model-00016-of-00022.safetensors",
-    "transformer.encoder.layers.30.mlp.dense_4h_to_h.weight": "model-00017-of-00022.safetensors",
-    "transformer.encoder.layers.30.mlp.dense_h_to_4h.weight": "model-00017-of-00022.safetensors",
-    "transformer.encoder.layers.30.post_attention_layernorm.weight": "model-00016-of-00022.safetensors",
-    "transformer.encoder.layers.30.self_attention.dense.weight": "model-00016-of-00022.safetensors",
-    "transformer.encoder.layers.30.self_attention.query_key_value.bias": "model-00016-of-00022.safetensors",
-    "transformer.encoder.layers.30.self_attention.query_key_value.weight": "model-00016-of-00022.safetensors",
-    "transformer.encoder.layers.31.input_layernorm.weight": "model-00017-of-00022.safetensors",
-    "transformer.encoder.layers.31.mlp.dense_4h_to_h.weight": "model-00017-of-00022.safetensors",
-    "transformer.encoder.layers.31.mlp.dense_h_to_4h.weight": "model-00017-of-00022.safetensors",
-    "transformer.encoder.layers.31.post_attention_layernorm.weight": "model-00017-of-00022.safetensors",
-    "transformer.encoder.layers.31.self_attention.dense.weight": "model-00017-of-00022.safetensors",
-    "transformer.encoder.layers.31.self_attention.query_key_value.bias": "model-00017-of-00022.safetensors",
-    "transformer.encoder.layers.31.self_attention.query_key_value.weight": "model-00017-of-00022.safetensors",
-    "transformer.encoder.layers.32.input_layernorm.weight": "model-00017-of-00022.safetensors",
-    "transformer.encoder.layers.32.mlp.dense_4h_to_h.weight": "model-00018-of-00022.safetensors",
-    "transformer.encoder.layers.32.mlp.dense_h_to_4h.weight": "model-00018-of-00022.safetensors",
-    "transformer.encoder.layers.32.post_attention_layernorm.weight": "model-00017-of-00022.safetensors",
-    "transformer.encoder.layers.32.self_attention.dense.weight": "model-00017-of-00022.safetensors",
-    "transformer.encoder.layers.32.self_attention.query_key_value.bias": "model-00017-of-00022.safetensors",
-    "transformer.encoder.layers.32.self_attention.query_key_value.weight": "model-00017-of-00022.safetensors",
-    "transformer.encoder.layers.33.input_layernorm.weight": "model-00018-of-00022.safetensors",
-    "transformer.encoder.layers.33.mlp.dense_4h_to_h.weight": "model-00018-of-00022.safetensors",
-    "transformer.encoder.layers.33.mlp.dense_h_to_4h.weight": "model-00018-of-00022.safetensors",
-    "transformer.encoder.layers.33.post_attention_layernorm.weight": "model-00018-of-00022.safetensors",
-    "transformer.encoder.layers.33.self_attention.dense.weight": "model-00018-of-00022.safetensors",
-    "transformer.encoder.layers.33.self_attention.query_key_value.bias": "model-00018-of-00022.safetensors",
-    "transformer.encoder.layers.33.self_attention.query_key_value.weight": "model-00018-of-00022.safetensors",
-    "transformer.encoder.layers.34.input_layernorm.weight": "model-00018-of-00022.safetensors",
-    "transformer.encoder.layers.34.mlp.dense_4h_to_h.weight": "model-00019-of-00022.safetensors",
-    "transformer.encoder.layers.34.mlp.dense_h_to_4h.weight": "model-00019-of-00022.safetensors",
-    "transformer.encoder.layers.34.post_attention_layernorm.weight": "model-00018-of-00022.safetensors",
-    "transformer.encoder.layers.34.self_attention.dense.weight": "model-00018-of-00022.safetensors",
-    "transformer.encoder.layers.34.self_attention.query_key_value.bias": "model-00018-of-00022.safetensors",
-    "transformer.encoder.layers.34.self_attention.query_key_value.weight": "model-00018-of-00022.safetensors",
-    "transformer.encoder.layers.35.input_layernorm.weight": "model-00019-of-00022.safetensors",
-    "transformer.encoder.layers.35.mlp.dense_4h_to_h.weight": "model-00019-of-00022.safetensors",
-    "transformer.encoder.layers.35.mlp.dense_h_to_4h.weight": "model-00019-of-00022.safetensors",
-    "transformer.encoder.layers.35.post_attention_layernorm.weight": "model-00019-of-00022.safetensors",
-    "transformer.encoder.layers.35.self_attention.dense.weight": "model-00019-of-00022.safetensors",
-    "transformer.encoder.layers.35.self_attention.query_key_value.bias": "model-00019-of-00022.safetensors",
-    "transformer.encoder.layers.35.self_attention.query_key_value.weight": "model-00019-of-00022.safetensors",
-    "transformer.encoder.layers.36.input_layernorm.weight": "model-00019-of-00022.safetensors",
-    "transformer.encoder.layers.36.mlp.dense_4h_to_h.weight": "model-00020-of-00022.safetensors",
-    "transformer.encoder.layers.36.mlp.dense_h_to_4h.weight": "model-00020-of-00022.safetensors",
-    "transformer.encoder.layers.36.post_attention_layernorm.weight": "model-00019-of-00022.safetensors",
-    "transformer.encoder.layers.36.self_attention.dense.weight": "model-00019-of-00022.safetensors",
-    "transformer.encoder.layers.36.self_attention.query_key_value.bias": "model-00019-of-00022.safetensors",
-    "transformer.encoder.layers.36.self_attention.query_key_value.weight": "model-00019-of-00022.safetensors",
-    "transformer.encoder.layers.37.input_layernorm.weight": "model-00020-of-00022.safetensors",
-    "transformer.encoder.layers.37.mlp.dense_4h_to_h.weight": "model-00020-of-00022.safetensors",
-    "transformer.encoder.layers.37.mlp.dense_h_to_4h.weight": "model-00020-of-00022.safetensors",
-    "transformer.encoder.layers.37.post_attention_layernorm.weight": "model-00020-of-00022.safetensors",
-    "transformer.encoder.layers.37.self_attention.dense.weight": "model-00020-of-00022.safetensors",
-    "transformer.encoder.layers.37.self_attention.query_key_value.bias": "model-00020-of-00022.safetensors",
-    "transformer.encoder.layers.37.self_attention.query_key_value.weight": "model-00020-of-00022.safetensors",
-    "transformer.encoder.layers.38.input_layernorm.weight": "model-00020-of-00022.safetensors",
-    "transformer.encoder.layers.38.mlp.dense_4h_to_h.weight": "model-00021-of-00022.safetensors",
-    "transformer.encoder.layers.38.mlp.dense_h_to_4h.weight": "model-00021-of-00022.safetensors",
-    "transformer.encoder.layers.38.post_attention_layernorm.weight": "model-00020-of-00022.safetensors",
-    "transformer.encoder.layers.38.self_attention.dense.weight": "model-00020-of-00022.safetensors",
-    "transformer.encoder.layers.38.self_attention.query_key_value.bias": "model-00020-of-00022.safetensors",
-    "transformer.encoder.layers.38.self_attention.query_key_value.weight": "model-00020-of-00022.safetensors",
-    "transformer.encoder.layers.39.input_layernorm.weight": "model-00021-of-00022.safetensors",
-    "transformer.encoder.layers.39.mlp.dense_4h_to_h.weight": "model-00021-of-00022.safetensors",
-    "transformer.encoder.layers.39.mlp.dense_h_to_4h.weight": "model-00021-of-00022.safetensors",
-    "transformer.encoder.layers.39.post_attention_layernorm.weight": "model-00021-of-00022.safetensors",
-    "transformer.encoder.layers.39.self_attention.dense.weight": "model-00021-of-00022.safetensors",
-    "transformer.encoder.layers.39.self_attention.query_key_value.bias": "model-00021-of-00022.safetensors",
-    "transformer.encoder.layers.39.self_attention.query_key_value.weight": "model-00021-of-00022.safetensors",
-    "transformer.encoder.layers.4.input_layernorm.weight": "model-00003-of-00022.safetensors",
-    "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "model-00004-of-00022.safetensors",
-    "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "model-00004-of-00022.safetensors",
-    "transformer.encoder.layers.4.post_attention_layernorm.weight": "model-00003-of-00022.safetensors",
-    "transformer.encoder.layers.4.self_attention.dense.weight": "model-00003-of-00022.safetensors",
-    "transformer.encoder.layers.4.self_attention.query_key_value.bias": "model-00003-of-00022.safetensors",
-    "transformer.encoder.layers.4.self_attention.query_key_value.weight": "model-00003-of-00022.safetensors",
-    "transformer.encoder.layers.5.input_layernorm.weight": "model-00004-of-00022.safetensors",
-    "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "model-00004-of-00022.safetensors",
-    "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "model-00004-of-00022.safetensors",
-    "transformer.encoder.layers.5.post_attention_layernorm.weight": "model-00004-of-00022.safetensors",
-    "transformer.encoder.layers.5.self_attention.dense.weight": "model-00004-of-00022.safetensors",
-    "transformer.encoder.layers.5.self_attention.query_key_value.bias": "model-00004-of-00022.safetensors",
-    "transformer.encoder.layers.5.self_attention.query_key_value.weight": "model-00004-of-00022.safetensors",
-    "transformer.encoder.layers.6.input_layernorm.weight": "model-00004-of-00022.safetensors",
-    "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "model-00005-of-00022.safetensors",
-    "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "model-00005-of-00022.safetensors",
-    "transformer.encoder.layers.6.post_attention_layernorm.weight": "model-00004-of-00022.safetensors",
-    "transformer.encoder.layers.6.self_attention.dense.weight": "model-00004-of-00022.safetensors",
-    "transformer.encoder.layers.6.self_attention.query_key_value.bias": "model-00004-of-00022.safetensors",
-    "transformer.encoder.layers.6.self_attention.query_key_value.weight": "model-00004-of-00022.safetensors",
-    "transformer.encoder.layers.7.input_layernorm.weight": "model-00005-of-00022.safetensors",
-    "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "model-00005-of-00022.safetensors",
-    "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "model-00005-of-00022.safetensors",
-    "transformer.encoder.layers.7.post_attention_layernorm.weight": "model-00005-of-00022.safetensors",
-    "transformer.encoder.layers.7.self_attention.dense.weight": "model-00005-of-00022.safetensors",
-    "transformer.encoder.layers.7.self_attention.query_key_value.bias": "model-00005-of-00022.safetensors",
-    "transformer.encoder.layers.7.self_attention.query_key_value.weight": "model-00005-of-00022.safetensors",
-    "transformer.encoder.layers.8.input_layernorm.weight": "model-00005-of-00022.safetensors",
-    "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "model-00006-of-00022.safetensors",
-    "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "model-00006-of-00022.safetensors",
-    "transformer.encoder.layers.8.post_attention_layernorm.weight": "model-00005-of-00022.safetensors",
-    "transformer.encoder.layers.8.self_attention.dense.weight": "model-00005-of-00022.safetensors",
-    "transformer.encoder.layers.8.self_attention.query_key_value.bias": "model-00005-of-00022.safetensors",
-    "transformer.encoder.layers.8.self_attention.query_key_value.weight": "model-00005-of-00022.safetensors",
-    "transformer.encoder.layers.9.input_layernorm.weight": "model-00006-of-00022.safetensors",
-    "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "model-00006-of-00022.safetensors",
-    "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "model-00006-of-00022.safetensors",
-    "transformer.encoder.layers.9.post_attention_layernorm.weight": "model-00006-of-00022.safetensors",
-    "transformer.encoder.layers.9.self_attention.dense.weight": "model-00006-of-00022.safetensors",
-    "transformer.encoder.layers.9.self_attention.query_key_value.bias": "model-00006-of-00022.safetensors",
-    "transformer.encoder.layers.9.self_attention.query_key_value.weight": "model-00006-of-00022.safetensors",
-    "transformer.output_layer.weight": "model-00022-of-00022.safetensors",
-    "transformer.rotary_pos_emb.inv_freq": "model-00002-of-00022.safetensors"
+    "transformer.embedding.word_embeddings.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.final_layernorm.weight": "model-00007-of-00007.safetensors",
+    "transformer.encoder.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.0.self_attention.dense.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.0.self_attention.query_key_value.bias": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.0.self_attention.query_key_value.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.1.self_attention.dense.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.1.self_attention.query_key_value.bias": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.1.self_attention.query_key_value.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.10.self_attention.dense.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.10.self_attention.query_key_value.bias": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.10.self_attention.query_key_value.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.11.self_attention.dense.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.11.self_attention.query_key_value.bias": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.11.self_attention.query_key_value.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.12.self_attention.dense.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.12.self_attention.query_key_value.bias": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.12.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.13.self_attention.dense.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.13.self_attention.query_key_value.bias": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.13.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.14.self_attention.dense.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.14.self_attention.query_key_value.bias": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.14.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.15.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.15.self_attention.dense.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.15.self_attention.query_key_value.bias": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.15.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.16.self_attention.dense.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.16.self_attention.query_key_value.bias": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.16.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.17.self_attention.dense.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.17.self_attention.query_key_value.bias": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.17.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.18.self_attention.dense.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.18.self_attention.query_key_value.bias": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.18.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors",
+    "transformer.encoder.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.19.self_attention.dense.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.19.self_attention.query_key_value.bias": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.19.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.2.self_attention.dense.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.2.self_attention.query_key_value.bias": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.2.self_attention.query_key_value.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.20.self_attention.dense.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.20.self_attention.query_key_value.bias": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.20.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.21.self_attention.dense.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.21.self_attention.query_key_value.bias": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.21.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.22.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.22.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.22.self_attention.dense.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.22.self_attention.query_key_value.bias": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.22.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.23.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.23.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.23.self_attention.dense.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.23.self_attention.query_key_value.bias": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.23.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.24.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.24.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.24.self_attention.dense.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.24.self_attention.query_key_value.bias": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.24.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.25.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.25.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.25.self_attention.dense.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.25.self_attention.query_key_value.bias": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.25.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors",
+    "transformer.encoder.layers.26.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.26.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.26.self_attention.dense.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.26.self_attention.query_key_value.bias": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.26.self_attention.query_key_value.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.27.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.27.self_attention.dense.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.27.self_attention.query_key_value.bias": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.27.self_attention.query_key_value.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.28.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.28.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.28.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.28.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.28.self_attention.dense.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.28.self_attention.query_key_value.bias": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.28.self_attention.query_key_value.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.29.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.29.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.29.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.29.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.29.self_attention.dense.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.29.self_attention.query_key_value.bias": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.29.self_attention.query_key_value.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.3.self_attention.dense.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.3.self_attention.query_key_value.bias": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.3.self_attention.query_key_value.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.30.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.30.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.30.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.30.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.30.self_attention.dense.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.30.self_attention.query_key_value.bias": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.30.self_attention.query_key_value.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.31.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.31.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.31.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.31.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.31.self_attention.dense.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.31.self_attention.query_key_value.bias": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.31.self_attention.query_key_value.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.32.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.32.mlp.dense_4h_to_h.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.32.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.32.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.32.self_attention.dense.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.32.self_attention.query_key_value.bias": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.32.self_attention.query_key_value.weight": "model-00005-of-00007.safetensors",
+    "transformer.encoder.layers.33.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.33.mlp.dense_4h_to_h.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.33.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.33.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.33.self_attention.dense.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.33.self_attention.query_key_value.bias": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.33.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.34.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.34.mlp.dense_4h_to_h.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.34.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.34.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.34.self_attention.dense.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.34.self_attention.query_key_value.bias": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.34.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.35.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.35.mlp.dense_4h_to_h.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.35.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.35.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.35.self_attention.dense.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.35.self_attention.query_key_value.bias": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.35.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.36.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.36.mlp.dense_4h_to_h.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.36.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.36.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.36.self_attention.dense.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.36.self_attention.query_key_value.bias": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.36.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.37.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.37.mlp.dense_4h_to_h.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.37.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.37.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.37.self_attention.dense.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.37.self_attention.query_key_value.bias": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.37.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.38.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.38.mlp.dense_4h_to_h.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.38.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.38.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.38.self_attention.dense.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.38.self_attention.query_key_value.bias": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.38.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.39.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.39.mlp.dense_4h_to_h.weight": "model-00007-of-00007.safetensors",
+    "transformer.encoder.layers.39.mlp.dense_h_to_4h.weight": "model-00007-of-00007.safetensors",
+    "transformer.encoder.layers.39.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.39.self_attention.dense.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.39.self_attention.query_key_value.bias": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.39.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors",
+    "transformer.encoder.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.4.self_attention.dense.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.4.self_attention.query_key_value.bias": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.4.self_attention.query_key_value.weight": "model-00001-of-00007.safetensors",
+    "transformer.encoder.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.5.self_attention.dense.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.5.self_attention.query_key_value.bias": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.5.self_attention.query_key_value.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.6.self_attention.dense.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.6.self_attention.query_key_value.bias": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.6.self_attention.query_key_value.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.7.self_attention.dense.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.7.self_attention.query_key_value.bias": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.7.self_attention.query_key_value.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.8.self_attention.dense.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.8.self_attention.query_key_value.bias": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.8.self_attention.query_key_value.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.9.self_attention.dense.weight": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.9.self_attention.query_key_value.bias": "model-00002-of-00007.safetensors",
+    "transformer.encoder.layers.9.self_attention.query_key_value.weight": "model-00002-of-00007.safetensors",
+    "transformer.output_layer.weight": "model-00007-of-00007.safetensors",
+    "transformer.rotary_pos_emb.inv_freq": "model-00001-of-00007.safetensors"
   }
 }