Upload folder using huggingface_hub

config.json

@@ -1,7 +1,6 @@
 {
-  "_name_or_path": "KYLN24/tmp-Llama-2-7b-chat-hf-webshop-eto",
+  "_name_or_path": "/fs-computility/llm/guohonglin/agent-workspace/ETO/save_path/tmp-Llama-2-7b-chat-hf-webshop-dpo-iter-3",
   "architectures": [
-    "LlamaModel",
     "LlamaForCausalLM"
   ],
   "attention_bias": false,

generation_config.json

@@ -6,5 +6,5 @@
   "pad_token_id": 0,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.32.0.dev0"
+  "transformers_version": "4.39.3"
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72209934a60792d93d87efe8a687a55cb14d718d04d212150428fb05407233fe
-size 4938984720
+oid sha256:13c78ef2575afb0b36be2850c55f2cbcce689278c3079d9af2922d4fc7abc80b
+size 4938985352

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b160eac32d8eb1ddeea289402b3e3636e8e7414b62618249b5758f65286c785
-size 4947390224
+oid sha256:ea70e83b4debb04e57dae20b614aa20f0cc83613c9a4f9917116eadce81a0821
+size 4947390880

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e196da24afe7773148ec74975a4103eee6e7f2f7610b33b1c3f2dc42eb8c065
-size 3328344240
+oid sha256:2c3098326d0afe4be095552a27e24445c0d18d0d55be2b6b4bfe1106ea58a223
+size 3590488816

model.safetensors.index.json

@@ -1,297 +1,298 @@
 {
   "metadata": {
-    "total_size": 13214687232
+    "total_size": 13476831232
   },
   "weight_map": {
-    "embed_tokens.weight": "model-00001-of-00003.safetensors",
-    "layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "norm.weight": "model-00003-of-00003.safetensors"
+    "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

@@ -13,6 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer_config.json

@@ -1,36 +1,44 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
   },
+  "bos_token": "<s>",
   "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "eos_token": "</s>",
   "legacy": false,
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": null,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
   "padding_side": "right",
   "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
 }