New format using native Transformers model

.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

@@ -1,43 +1,32 @@
 {
-  "_name_or_path": "THUDM/glm-4-9b",
-  "model_type": "chatglm",
   "architectures": [
-    "ChatGLMModel"
+    "GlmForCausalLM"
   ],
-  "auto_map": {
-    "AutoConfig": "configuration_chatglm.ChatGLMConfig",
-    "AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
-    "AutoModelForCausalLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
-    "AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
-    "AutoModelForSequenceClassification": "modeling_chatglm.ChatGLMForSequenceClassification"
-  },
-  "add_bias_linear": false,
-  "add_qkv_bias": true,
-  "apply_query_key_layer_scaling": true,
-  "apply_residual_connection_post_layernorm": false,
+  "attention_bias": true,
   "attention_dropout": 0.0,
-  "attention_softmax_in_fp32": true,
-  "attn_implementation": "sdpa",
-  "bias_dropout_fusion": true,
-  "ffn_hidden_size": 13696,
-  "fp32_residual_connection": false,
-  "hidden_dropout": 0.0,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
   "hidden_size": 4096,
-  "kv_channels": 128,
-  "layernorm_epsilon": 0.00000015625,
-  "multi_query_attention": true,
-  "multi_query_group_num": 2,
+  "initializer_range": 0.02,
+  "intermediate_size": 13696,
+  "linear_bias": false,
+  "max_position_embeddings": 8192,
+  "model_type": "glm",
   "num_attention_heads": 32,
-  "num_layers": 40,
-  "original_rope": true,
-  "padded_vocab_size": 151552,
-  "post_layer_norm": true,
-  "rmsnorm": true,
-  "seq_length": 8192,
-  "use_cache": true,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.44.0",
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151329,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1.5625e-07,
+  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "eos_token_id": [151329, 151336, 151338],
-  "pad_token_id": 151329
-}
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0.dev0",
+  "use_cache": true,
+  "vocab_size": 151552
+}

generation_config.json

@@ -1,13 +1,10 @@
 {
+  "_from_model_config": true,
   "eos_token_id": [
     151329,
     151336,
     151338
   ],
   "pad_token_id": 151329,
-  "do_sample": true,
-  "temperature": 0.8,
-  "max_length": 8192,
-  "top_p": 0.8,
-  "transformers_version": "4.44.0"
-}
+  "transformers_version": "4.46.0.dev0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c94966b5c961cb03e2d15a3103fd08002dc02d8a7b00d528f0e6faf46ac40de3
+size 4984129144

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07b2ebcd532f6da995284a884f0a29361f9e92624503868eae3493643728f10e
+size 4895069784

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31c864adce492578e2e96516bd84cf40ae663396c930002471be374f0f77cd80
+size 4895069792

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0a16cfb2b9d92687b735bfc01fba76337c547b5c382c18a958c4048c76716ca
+size 4025667040

model.safetensors.index.json

@@ -1,291 +1,290 @@
 {
   "metadata": {
-    "total_size": 18799902784
+    "total_size": 18799902720
   },
   "weight_map": {
-    "transformer.embedding.word_embeddings.weight": "model-00001-of-00010.safetensors",
-    "transformer.encoder.final_layernorm.weight": "model-00010-of-00010.safetensors",
-    "transformer.encoder.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors",
-    "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00010.safetensors",
-    "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00010.safetensors",
-    "transformer.encoder.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
-    "transformer.encoder.layers.0.self_attention.dense.weight": "model-00001-of-00010.safetensors",
-    "transformer.encoder.layers.0.self_attention.query_key_value.bias": "model-00001-of-00010.safetensors",
-    "transformer.encoder.layers.0.self_attention.query_key_value.weight": "model-00001-of-00010.safetensors",
-    "transformer.encoder.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors",
-    "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00010.safetensors",
-    "transformer.encoder.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
-    "transformer.encoder.layers.1.self_attention.dense.weight": "model-00001-of-00010.safetensors",
-    "transformer.encoder.layers.1.self_attention.query_key_value.bias": "model-00001-of-00010.safetensors",
-    "transformer.encoder.layers.1.self_attention.query_key_value.weight": "model-00001-of-00010.safetensors",
-    "transformer.encoder.layers.10.input_layernorm.weight": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.10.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.10.self_attention.dense.weight": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.10.self_attention.query_key_value.bias": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.10.self_attention.query_key_value.weight": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.11.input_layernorm.weight": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.11.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.11.self_attention.dense.weight": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.11.self_attention.query_key_value.bias": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.11.self_attention.query_key_value.weight": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.12.input_layernorm.weight": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.12.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.12.self_attention.dense.weight": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.12.self_attention.query_key_value.bias": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.12.self_attention.query_key_value.weight": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.13.input_layernorm.weight": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.13.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.13.self_attention.dense.weight": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.13.self_attention.query_key_value.bias": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.13.self_attention.query_key_value.weight": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.14.input_layernorm.weight": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.14.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.14.self_attention.dense.weight": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.14.self_attention.query_key_value.bias": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.14.self_attention.query_key_value.weight": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.15.input_layernorm.weight": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.15.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.15.self_attention.dense.weight": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.15.self_attention.query_key_value.bias": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.15.self_attention.query_key_value.weight": "model-00004-of-00010.safetensors",
-    "transformer.encoder.layers.16.input_layernorm.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.16.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.16.self_attention.dense.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.16.self_attention.query_key_value.bias": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.16.self_attention.query_key_value.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.17.input_layernorm.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.17.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.17.self_attention.dense.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.17.self_attention.query_key_value.bias": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.17.self_attention.query_key_value.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.18.input_layernorm.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.18.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.18.self_attention.dense.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.18.self_attention.query_key_value.bias": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.18.self_attention.query_key_value.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.19.input_layernorm.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.19.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.19.self_attention.dense.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.19.self_attention.query_key_value.bias": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.19.self_attention.query_key_value.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.2.input_layernorm.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.2.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.2.self_attention.dense.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.2.self_attention.query_key_value.bias": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.2.self_attention.query_key_value.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.20.input_layernorm.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.20.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.20.self_attention.dense.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.20.self_attention.query_key_value.bias": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.20.self_attention.query_key_value.weight": "model-00005-of-00010.safetensors",
-    "transformer.encoder.layers.21.input_layernorm.weight": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.21.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.21.self_attention.dense.weight": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.21.self_attention.query_key_value.bias": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.21.self_attention.query_key_value.weight": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.22.input_layernorm.weight": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.22.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.22.self_attention.dense.weight": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.22.self_attention.query_key_value.bias": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.22.self_attention.query_key_value.weight": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.23.input_layernorm.weight": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.23.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.23.self_attention.dense.weight": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.23.self_attention.query_key_value.bias": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.23.self_attention.query_key_value.weight": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.24.input_layernorm.weight": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.24.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.24.self_attention.dense.weight": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.24.self_attention.query_key_value.bias": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.24.self_attention.query_key_value.weight": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.25.input_layernorm.weight": "model-00006-of-00010.safetensors",
-    "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.25.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.25.self_attention.dense.weight": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.25.self_attention.query_key_value.bias": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.25.self_attention.query_key_value.weight": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.26.input_layernorm.weight": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.26.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.26.self_attention.dense.weight": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.26.self_attention.query_key_value.bias": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.26.self_attention.query_key_value.weight": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.27.input_layernorm.weight": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.27.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.27.self_attention.dense.weight": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.27.self_attention.query_key_value.bias": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.27.self_attention.query_key_value.weight": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.28.input_layernorm.weight": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.28.mlp.dense_4h_to_h.weight": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.28.mlp.dense_h_to_4h.weight": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.28.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.28.self_attention.dense.weight": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.28.self_attention.query_key_value.bias": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.28.self_attention.query_key_value.weight": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.29.input_layernorm.weight": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.29.mlp.dense_4h_to_h.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.29.mlp.dense_h_to_4h.weight": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.29.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.29.self_attention.dense.weight": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.29.self_attention.query_key_value.bias": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.29.self_attention.query_key_value.weight": "model-00007-of-00010.safetensors",
-    "transformer.encoder.layers.3.input_layernorm.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.3.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.3.self_attention.dense.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.3.self_attention.query_key_value.bias": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.3.self_attention.query_key_value.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.30.input_layernorm.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.30.mlp.dense_4h_to_h.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.30.mlp.dense_h_to_4h.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.30.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.30.self_attention.dense.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.30.self_attention.query_key_value.bias": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.30.self_attention.query_key_value.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.31.input_layernorm.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.31.mlp.dense_4h_to_h.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.31.mlp.dense_h_to_4h.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.31.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.31.self_attention.dense.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.31.self_attention.query_key_value.bias": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.31.self_attention.query_key_value.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.32.input_layernorm.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.32.mlp.dense_4h_to_h.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.32.mlp.dense_h_to_4h.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.32.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.32.self_attention.dense.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.32.self_attention.query_key_value.bias": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.32.self_attention.query_key_value.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.33.input_layernorm.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.33.mlp.dense_4h_to_h.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.33.mlp.dense_h_to_4h.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.33.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.33.self_attention.dense.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.33.self_attention.query_key_value.bias": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.33.self_attention.query_key_value.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.34.input_layernorm.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.34.mlp.dense_4h_to_h.weight": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.34.mlp.dense_h_to_4h.weight": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.34.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.34.self_attention.dense.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.34.self_attention.query_key_value.bias": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.34.self_attention.query_key_value.weight": "model-00008-of-00010.safetensors",
-    "transformer.encoder.layers.35.input_layernorm.weight": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.35.mlp.dense_4h_to_h.weight": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.35.mlp.dense_h_to_4h.weight": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.35.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.35.self_attention.dense.weight": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.35.self_attention.query_key_value.bias": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.35.self_attention.query_key_value.weight": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.36.input_layernorm.weight": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.36.mlp.dense_4h_to_h.weight": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.36.mlp.dense_h_to_4h.weight": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.36.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.36.self_attention.dense.weight": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.36.self_attention.query_key_value.bias": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.36.self_attention.query_key_value.weight": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.37.input_layernorm.weight": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.37.mlp.dense_4h_to_h.weight": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.37.mlp.dense_h_to_4h.weight": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.37.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.37.self_attention.dense.weight": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.37.self_attention.query_key_value.bias": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.37.self_attention.query_key_value.weight": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.38.input_layernorm.weight": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.38.mlp.dense_4h_to_h.weight": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.38.mlp.dense_h_to_4h.weight": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.38.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.38.self_attention.dense.weight": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.38.self_attention.query_key_value.bias": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.38.self_attention.query_key_value.weight": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.39.input_layernorm.weight": "model-00009-of-00010.safetensors",
-    "transformer.encoder.layers.39.mlp.dense_4h_to_h.weight": "model-00010-of-00010.safetensors",
-    "transformer.encoder.layers.39.mlp.dense_h_to_4h.weight": "model-00010-of-00010.safetensors",
-    "transformer.encoder.layers.39.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
-    "transformer.encoder.layers.39.self_attention.dense.weight": "model-00010-of-00010.safetensors",
-    "transformer.encoder.layers.39.self_attention.query_key_value.bias": "model-00010-of-00010.safetensors",
-    "transformer.encoder.layers.39.self_attention.query_key_value.weight": "model-00010-of-00010.safetensors",
-    "transformer.encoder.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.4.self_attention.dense.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.4.self_attention.query_key_value.bias": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.4.self_attention.query_key_value.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.5.input_layernorm.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.5.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.5.self_attention.dense.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.5.self_attention.query_key_value.bias": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.5.self_attention.query_key_value.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.6.input_layernorm.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.6.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.6.self_attention.dense.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.6.self_attention.query_key_value.bias": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.6.self_attention.query_key_value.weight": "model-00002-of-00010.safetensors",
-    "transformer.encoder.layers.7.input_layernorm.weight": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.7.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.7.self_attention.dense.weight": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.7.self_attention.query_key_value.bias": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.7.self_attention.query_key_value.weight": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.8.input_layernorm.weight": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.8.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.8.self_attention.dense.weight": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.8.self_attention.query_key_value.bias": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.8.self_attention.query_key_value.weight": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.9.input_layernorm.weight": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.9.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.9.self_attention.dense.weight": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.9.self_attention.query_key_value.bias": "model-00003-of-00010.safetensors",
-    "transformer.encoder.layers.9.self_attention.query_key_value.weight": "model-00003-of-00010.safetensors",
-    "transformer.output_layer.weight": "model-00010-of-00010.safetensors",
-    "transformer.rotary_pos_emb.inv_freq": "model-00001-of-00010.safetensors"
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.qkv_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.qkv_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.qkv_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.qkv_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.qkv_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.qkv_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.qkv_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.qkv_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.qkv_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.qkv_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.qkv_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.qkv_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.qkv_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.qkv_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.qkv_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.qkv_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.qkv_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.qkv_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.qkv_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.qkv_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.qkv_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.qkv_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.qkv_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.qkv_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.qkv_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.qkv_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.qkv_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.qkv_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.qkv_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.qkv_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.qkv_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.qkv_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.qkv_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.qkv_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
   }
 }

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a7269d6daa6328de533def0082ff9d3a825bb89036cbcc665c324f941f67fbf
+size 19967863

tokenizer_config.json

@@ -1,10 +1,4 @@
 {
-  "auto_map": {
-    "AutoTokenizer": [
-      "tokenization_chatglm.ChatGLM4Tokenizer",
-      null
-    ]
-  },
   "added_tokens_decoder": {
     "151329": {
       "content": "<|endoftext|>",
@@ -119,15 +113,27 @@
       "special": true
     }
   },
-  "additional_special_tokens": ["<|endoftext|>", "[MASK]", "[gMASK]", "[sMASK]", "<sop>", "<eop>", "<|system|>",
-                               "<|user|>", "<|assistant|>", "<|observation|>", "<|begin_of_image|>", "<|end_of_image|>",
-                               "<|begin_of_video|>", "<|end_of_video|>"],
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>"
+  ],
+  "bos_token": null,
   "clean_up_tokenization_spaces": false,
-  "do_lower_case": false,
   "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<|endoftext|>",
-  "model_max_length": 8000,
   "padding_side": "left",
-  "remove_space": false,
-  "tokenizer_class": "ChatGLM4Tokenizer"
+  "tokenizer_class": "PreTrainedTokenizerFast"
 }