Upload ChatGlmForCausalLM

config.json

@@ -1,42 +1,41 @@
 {
-  "_name_or_path": "THUDM/chatglm3-6b",
-  "model_type": "chatglm",
+  "_name_or_path": "ybelkada/chatglm3-6b-hf",
+  "apply_query_key_layer_scaling": true,
   "architectures": [
-    "ChatGLMModel"
+    "ChatGlmForCausalLM"
   ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
   "auto_map": {
-    "AutoConfig": "configuration_chatglm.ChatGLMConfig",
-    "AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
-    "AutoModelForCausalLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
-    "AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
-    "AutoModelForSequenceClassification": "modeling_chatglm.ChatGLMForSequenceClassification"
+    "AutoConfig": "ybelkada/chatglm3-6b-hf--configuration_chatglm.ChatGLMConfig",
+    "AutoModel": "ybelkada/chatglm3-6b-hf--modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForCausalLM": "ybelkada/chatglm3-6b-hf--modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForSeq2SeqLM": "ybelkada/chatglm3-6b-hf--modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForSequenceClassification": "ybelkada/chatglm3-6b-hf--modeling_chatglm.ChatGLMForSequenceClassification"
   },
-  "add_bias_linear": false,
-  "add_qkv_bias": true,
-  "apply_query_key_layer_scaling": true,
-  "apply_residual_connection_post_layernorm": false,
-  "attention_dropout": 0.0,
-  "attention_softmax_in_fp32": true,
-  "bias_dropout_fusion": true,
-  "ffn_hidden_size": 13696,
-  "fp32_residual_connection": false,
-  "hidden_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
   "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 13696,
   "kv_channels": 128,
-  "layernorm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "chatglm",
   "multi_query_attention": true,
   "multi_query_group_num": 2,
   "num_attention_heads": 32,
-  "num_layers": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 32,
   "original_rope": true,
-  "padded_vocab_size": 65024,
-  "post_layer_norm": true,
-  "rmsnorm": true,
-  "seq_length": 8192,
-  "use_cache": true,
-  "torch_dtype": "float16",
-  "transformers_version": "4.30.2",
+  "partial_rotary_factor": 0.5,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "eos_token_id": 2,
-  "pad_token_id": 0
-}
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": true,
+  "vocab_size": 65024
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.37.0.dev0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3684a0fd31c8a00e061d1242bcf0faadb34a9d0c70fb64d6ab40c703337e1cbe
+size 4907609888

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39afb798e4edce6865d67d65a32aa6fd9b47f545937aed82f16837146bc6bc59
+size 4895070096

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffa10cbc5159b8962f44210eb4ff6d180bfe867ae6f0c88615b0e4f58a0b0158
+size 2684511912

model.safetensors.index.json

@@ -1,207 +1,206 @@
 {
-    "metadata": {
-        "total_size": 12487168064
-    },
-    "weight_map": {
-        "transformer.embedding.word_embeddings.weight": "model-00001-of-00007.safetensors",
-        "transformer.encoder.final_layernorm.weight": "model-00007-of-00007.safetensors",
-        "transformer.encoder.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
-        "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00007.safetensors",
-        "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00007.safetensors",
-        "transformer.encoder.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-        "transformer.encoder.layers.0.self_attention.dense.weight": "model-00001-of-00007.safetensors",
-        "transformer.encoder.layers.0.self_attention.query_key_value.bias": "model-00001-of-00007.safetensors",
-        "transformer.encoder.layers.0.self_attention.query_key_value.weight": "model-00001-of-00007.safetensors",
-        "transformer.encoder.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
-        "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00007.safetensors",
-        "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00007.safetensors",
-        "transformer.encoder.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-        "transformer.encoder.layers.1.self_attention.dense.weight": "model-00001-of-00007.safetensors",
-        "transformer.encoder.layers.1.self_attention.query_key_value.bias": "model-00001-of-00007.safetensors",
-        "transformer.encoder.layers.1.self_attention.query_key_value.weight": "model-00001-of-00007.safetensors",
-        "transformer.encoder.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.10.self_attention.dense.weight": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.10.self_attention.query_key_value.bias": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.10.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.11.self_attention.dense.weight": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.11.self_attention.query_key_value.bias": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.11.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.12.self_attention.dense.weight": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.12.self_attention.query_key_value.bias": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.12.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.13.self_attention.dense.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.13.self_attention.query_key_value.bias": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.13.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.14.self_attention.dense.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.14.self_attention.query_key_value.bias": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.14.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.15.self_attention.dense.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.15.self_attention.query_key_value.bias": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.15.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.16.self_attention.dense.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.16.self_attention.query_key_value.bias": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.16.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.17.self_attention.dense.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.17.self_attention.query_key_value.bias": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.17.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors",
-        "transformer.encoder.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.18.self_attention.dense.weight": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.18.self_attention.query_key_value.bias": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.18.self_attention.query_key_value.weight": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.19.self_attention.dense.weight": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.19.self_attention.query_key_value.bias": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.19.self_attention.query_key_value.weight": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
-        "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00007.safetensors",
-        "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00007.safetensors",
-        "transformer.encoder.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-        "transformer.encoder.layers.2.self_attention.dense.weight": "model-00001-of-00007.safetensors",
-        "transformer.encoder.layers.2.self_attention.query_key_value.bias": "model-00001-of-00007.safetensors",
-        "transformer.encoder.layers.2.self_attention.query_key_value.weight": "model-00001-of-00007.safetensors",
-        "transformer.encoder.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.20.self_attention.dense.weight": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.20.self_attention.query_key_value.bias": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.20.self_attention.query_key_value.weight": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.21.self_attention.dense.weight": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.21.self_attention.query_key_value.bias": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.21.self_attention.query_key_value.weight": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
-        "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.22.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.22.self_attention.dense.weight": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.22.self_attention.query_key_value.bias": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.22.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.23.input_layernorm.weight": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.23.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.23.self_attention.dense.weight": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.23.self_attention.query_key_value.bias": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.23.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.24.self_attention.dense.weight": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.24.self_attention.query_key_value.bias": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.24.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.25.self_attention.dense.weight": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.25.self_attention.query_key_value.bias": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.25.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "model-00007-of-00007.safetensors",
-        "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.26.self_attention.dense.weight": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.26.self_attention.query_key_value.bias": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.26.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors",
-        "transformer.encoder.layers.27.input_layernorm.weight": "model-00007-of-00007.safetensors",
-        "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "model-00007-of-00007.safetensors",
-        "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "model-00007-of-00007.safetensors",
-        "transformer.encoder.layers.27.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
-        "transformer.encoder.layers.27.self_attention.dense.weight": "model-00007-of-00007.safetensors",
-        "transformer.encoder.layers.27.self_attention.query_key_value.bias": "model-00007-of-00007.safetensors",
-        "transformer.encoder.layers.27.self_attention.query_key_value.weight": "model-00007-of-00007.safetensors",
-        "transformer.encoder.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
-        "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-        "transformer.encoder.layers.3.self_attention.dense.weight": "model-00001-of-00007.safetensors",
-        "transformer.encoder.layers.3.self_attention.query_key_value.bias": "model-00001-of-00007.safetensors",
-        "transformer.encoder.layers.3.self_attention.query_key_value.weight": "model-00001-of-00007.safetensors",
-        "transformer.encoder.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.4.self_attention.dense.weight": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.4.self_attention.query_key_value.bias": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.4.self_attention.query_key_value.weight": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.5.self_attention.dense.weight": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.5.self_attention.query_key_value.bias": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.5.self_attention.query_key_value.weight": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.6.self_attention.dense.weight": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.6.self_attention.query_key_value.bias": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.6.self_attention.query_key_value.weight": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.7.self_attention.dense.weight": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.7.self_attention.query_key_value.bias": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.7.self_attention.query_key_value.weight": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
-        "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.8.self_attention.dense.weight": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.8.self_attention.query_key_value.bias": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.8.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.9.self_attention.dense.weight": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.9.self_attention.query_key_value.bias": "model-00003-of-00007.safetensors",
-        "transformer.encoder.layers.9.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors",
-        "transformer.output_layer.weight": "model-00007-of-00007.safetensors",
-        "transformer.rotary_pos_emb.inv_freq": "model-00001-of-00007.safetensors"
-    }
-}
+  "metadata": {
+    "total_size": 12487168000
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}