Converting to native Transformers

.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

@@ -1,45 +1,30 @@
 {
-  "_name_or_path": "THUDM/glm-4-9b-chat-1m",
-  "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": 1.5625e-07,
-  "multi_query_attention": true,
-  "multi_query_group_num": 4,
+  "initializer_range": 0.02,
+  "intermediate_size": 13696,
+  "max_position_embeddings": 1048576,
+  "model_type": "glm",
   "num_attention_heads": 32,
   "num_hidden_layers": 40,
-  "num_layers": 40,
-  "rope_ratio": 10000,
-  "original_rope": true,
-  "padded_vocab_size": 151552,
-  "post_layer_norm": true,
-  "rmsnorm": true,
-  "seq_length": 1048576,
-  "use_cache": true,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.44.0",
+  "num_key_value_heads": 4,
+  "pad_token_id": 151329,
+  "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": 1024000,
-  "top_p": 0.8,
-  "transformers_version": "4.44.0"
-}
+  "transformers_version": "4.46.0.dev0"
+}

model-00001-of-00010.safetensors → model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6a585e72210e19d66595b5bdce096ab572bc4e42c04329846d2b94bc887a2be
-size 1953552416
+oid sha256:38c486f6290042de60272758cde3590e647c40f0ebd7aef8921741e17b38e1e8
+size 4992532328

model-00002-of-00010.safetensors → model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e6e53eed153711208b032e2321b199d61b1b13e5b4595b3e211683134737eb6
-size 1836194280
+oid sha256:7f86456944992b084c58297330465bbe19c67bf1b20ef31240f1c8fa54c26612
+size 4978973656

model-00003-of-00010.safetensors → model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da787c4e038ce18e59d2a28216519ad01369dc891f806eaae0814d1ed97325d4
-size 1985073224
+oid sha256:9d2d5e3fe3d3cf367518aff1e4774896c90be28995da6ef848516ad2594e61ec
+size 4945419120

model-00004-of-00010.safetensors → model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:472e89b06cf4bf977e3c74c40f1993dbd7acb1b73c42a343ba2f8734994715cc
-size 1948383632
+oid sha256:6c193084915ea9c45827b1e10c4612e7401c4efc7650a8a8c946105cb9495094
+size 4050841712

model-00005-of-00010.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:19f22af3a9b80c41cc010c77067c91b96955049faa8fe3e3a9c823ec5d723db1
-size 1836194312

model-00006-of-00010.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cec7a3e448a28b62eb394ea6ba358b173033b4c409d7f510cd8acb20d57716be
-size 1985073264

model-00007-of-00010.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:04f39b0f13224738f80991738350643653238ade66524b3b6f1751658abbd948
-size 1948383632

model-00008-of-00010.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ea76696ccd8b266eff2e755d9286a789a2b8d644a19b2cdccd365933e97cfa94
-size 1836194312

model-00009-of-00010.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6100cba5825057f51778ab70e4c4fdd4485a401a8ef97893bf6b36a8efd48ce3
-size 1985073264

model-00010-of-00010.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e12b9195e943b6561c6541008881350dc7488520b9938427c1a7b97ddc147283
-size 1653632040

model.safetensors.index.json

@@ -1,291 +1,450 @@
 {
   "metadata": {
-    "total_size": 18967715904
+    "total_size": 18967715840
   },
   "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.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.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.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.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.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_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.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_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.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_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.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_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.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_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.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_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.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.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.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.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.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.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.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.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.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.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.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.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.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.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.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_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.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_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.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_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.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_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.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_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.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_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.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_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.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_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.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.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.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_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.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_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.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_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.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_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.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.v_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.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.v_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.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.v_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.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.v_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.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.v_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.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.v_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.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.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.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.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.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.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.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.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.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.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.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
   }
 }

special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "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": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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|>",
@@ -119,16 +113,39 @@
       "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|>"],
-  "clean_up_tokenization_spaces": false,
+  "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|>"
+  ],
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_chatglm.ChatGLM4Tokenizer",
+      null
+    ]
+  },
   "chat_template": "[gMASK]<sop>{% for item in messages %}{% if item['tools'] is defined %}<|system|>\n你是一个名为 GLM-4 的人工智能助手。你是基于智谱AI训练的语言模型 GLM-4 模型开发的，你的任务是针对用户的问题和要求提供适当的答复和支持。\n\n# 可用工具{% set tools = item['tools'] %}{% for tool in tools %}{% if tool['type'] == 'function' %}\n\n## {{ tool['function']['name'] }}\n\n{{ tool['function'] | tojson(indent=4) }}\n在调用上述函数时，请使用 Json 格式表示调用的参数。{% elif tool['type'] == 'python' %}\n\n## python\n\n当你向 `python` 发送包含 Python 代码的消息时，该代码将会在一个有状态的 Jupyter notebook 环境中执行。\n`python` 返回代码执行的输出，或在执行 60 秒后返回超时。\n`/mnt/data` 将会持久化存储你的文件。在此会话中，`python` 无法访问互联网。不要使用 `python` 进行任何网络请求或者在线 API 调用，这些在线内容的访问将不会成功。{% elif tool['type'] == 'simple_browser' %}\n\n## simple_browser\n\n你可以使用 `simple_browser` 工具。该工具支持以下函数：\n`search(query: str, recency_days: int)`：使用搜索引擎进行查询并显示结果，可以使用 `recency_days` 参数控制搜索内容的时效性。\n`mclick(ids: list[int])`：获取一系列指定 id 的页面内容。每次调用时，须选择3-10个页面。选择多个角度的页面，同时尽可能选择可信任的信息来源。考虑到部分页面是无法加载的，你也可以多打开一些可能有用的页面而不用担心内容过多。\n`open_url(url: str)`：打开指定的 URL。\n\n使用 `【{引用 id}†{引用文本}】` 来引用内容。\n\n操作步骤：1. 使用 `search` 来获得信息列表; 2. 使用 `mclick` 来获取指定 ID 页面的内容; 3. 根据获得的内容进行回复。在回复中应当引用信息来源。\n 如果用户提供了 URL，也可以用 `open_url` 直接打开页面。\n如果初次搜索结果没有找到合适的信息，也可以再次使用 `search` 进行搜索。{% elif tool['type'] == 'cogview' %}\n\n## cogview\n\n如果用户的请求中包含了对图像的描述，你可以使用 `cogview` 来生成图像并展示给用户。你需要向 `cogview` 发送图像描述，规则：\n- 发送给 `cogview` 的消息必须使用英语。用户的中文描述必须完全翻译为英语。\n- 应当尽可能详细地描述图像生成的需求，需求描述约 100 英文单词。\n- 保持用户原始描述的意图。不要虚构内容或者没见过的人物。\n- 如无特殊说明，所在地为中国，持有中国立场并遵循中国社会主义价值观。{% endif %}{% endfor %}{% endif %}{% if item['content'] %}<|{{ item['role'] }}|>{{ item['metadata'] }}\n{{ item['content'] }}{% endif %}{% endfor %}{% if add_generation_prompt %}<|assistant|>{% endif %}",
+  "clean_up_tokenization_spaces": false,
   "do_lower_case": false,
   "eos_token": "<|endoftext|>",
-  "pad_token": "<|endoftext|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
   "model_max_length": 1024000,
+  "pad_token": "<|endoftext|>",
   "padding_side": "left",
   "remove_space": false,
-  "tokenizer_class": "ChatGLM4Tokenizer"
+  "tokenizer_class": "PreTrainedTokenizerFast"
 }