Upload folder using huggingface_hub

config.json

@@ -1,16 +1,19 @@
 {
-  "_name_or_path": "/ML-A100/team/mm/zhangge/gezhangmv/SKGLM/models/codellama-7b-instruct-hf",
+  "_name_or_path": "/home/azhuang/CodeLlama-7b-Instruct-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 11008,
   "max_position_embeddings": 16384,
+  "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
@@ -21,7 +24,7 @@
   "rope_theta": 1000000,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.34.0",
+  "transformers_version": "4.45.0",
   "use_cache": false,
-  "vocab_size": 32017
+  "vocab_size": 32016
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.34.0"
+  "transformers_version": "4.45.0"
 }

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:106f2be18cffc71d94bd3723e3db3c119f1c690a5e5653dbc5decaf52e145107
+size 4939116424

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ee55e66dfd0b59b06ebbae040671aa04c6564758dc36b6cf5aec9ef9aa66be5
+size 4947390880

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b411ec4a54fe493464d74f8a3484eed5c8eea732a96ba98e6a1fc848f2d5ccc4
+size 3590619888

model.safetensors.index.json

@@ -1,298 +1,298 @@
 {
-    "metadata": {
-        "total_size": 13477109760
-    },
-    "weight_map": {
-        "lm_head.weight": "model-00002-of-00002.safetensors",
-        "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
-        "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
-        "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-        "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
-        "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-        "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
-        "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-        "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
-        "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-        "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
-        "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-        "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
-        "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-        "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
-        "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-        "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
-        "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-        "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-        "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-        "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-        "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-        "model.norm.weight": "model-00002-of-00002.safetensors"
-    }
-}
+  "metadata": {
+    "total_size": 13477093376
+  },
+  "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.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

special_tokens_map.json

@@ -5,8 +5,26 @@
     "▁<SUF>",
     "▁<EOT>"
   ],
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "[PAD]",
-  "unk_token": "<unk>"
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -1,66 +1,60 @@
 {
+  "add_bos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
-      "lstrip": true,
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
     "1": {
       "content": "<s>",
-      "lstrip": true,
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
     "2": {
       "content": "</s>",
-      "lstrip": true,
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
     "32007": {
       "content": "▁<PRE>",
-      "lstrip": true,
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
     "32008": {
       "content": "▁<SUF>",
-      "lstrip": true,
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
     "32009": {
       "content": "▁<MID>",
-      "lstrip": true,
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
     "32010": {
       "content": "▁<EOT>",
-      "lstrip": true,
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32016": {
-      "content": "[PAD]",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     }
@@ -72,17 +66,19 @@
     "▁<EOT>"
   ],
   "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if loop.index0 == 0 and system_message is defined %}{% set content = '<<SYS>>\n' + system_message + '\n<</SYS>>\n\n' + message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ '<s>' + '[INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "eot_token": "▁<EOT>",
   "fill_token": "<FILL_ME>",
   "legacy": null,
   "middle_token": "▁<MID>",
-  "model_max_length": 2048,
-  "pad_token": "[PAD]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
   "padding_side": "right",
   "prefix_token": "▁<PRE>",
   "sp_model_kwargs": {},
+  "split_special_tokens": false,
   "suffix_token": "▁<SUF>",
   "tokenizer_class": "CodeLlamaTokenizer",
   "unk_token": "<unk>",