Trained with Unsloth

README.md

@@ -9,6 +9,7 @@ tags:
 - unsloth
 - llama
 - trl
+- sft
 ---
 
 # Uploaded  model

config.json

@@ -1,37 +1,30 @@
 {
-  "_name_or_path": "unsloth/meta-llama-3.1-8b-bnb-4bit",
+  "_name_or_path": "unsloth/mistral-7b-bnb-4bit",
   "architectures": [
-    "LlamaForCausalLM"
+    "MistralForCausalLM"
   ],
-  "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "eos_token_id": 128001,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
-  "max_position_embeddings": 131072,
-  "mlp_bias": false,
-  "model_type": "llama",
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
-  "pad_token_id": 128004,
-  "pretraining_tp": 1,
+  "pad_token_id": 0,
   "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "factor": 8.0,
-    "high_freq_factor": 4.0,
-    "low_freq_factor": 1.0,
-    "original_max_position_embeddings": 8192,
-    "rope_type": "llama3"
-  },
-  "rope_theta": 500000.0,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.44.2",
   "unsloth_version": "2024.8",
   "use_cache": true,
-  "vocab_size": 128256
+  "vocab_size": 32000
 }

generation_config.json

@@ -1,11 +1,8 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 128000,
-  "do_sample": true,
-  "eos_token_id": 128001,
-  "max_length": 131072,
-  "pad_token_id": 128004,
-  "temperature": 0.6,
-  "top_p": 0.9,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 32768,
+  "pad_token_id": 0,
   "transformers_version": "4.44.2"
 }

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15c9d888403ff579282b2321452a82ee3550505e934520e21eb76149afd98b94
+size 4943185632

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d6c6e5240913242ca3249d20b441dba41ffedbf227e6d81a0500e85c9b464b3
+size 4999844360

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a66b27aeb6e997aed4928dfff5ccbc9dd6f886fc0d723881f88630e052af9aa0
+size 4540536454

pytorch_model.bin.index.json

@@ -1,298 +1,298 @@
 {
   "metadata": {
-    "total_size": 16060522496
+    "total_size": 14483464192
   },
   "weight_map": {
-    "lm_head.weight": "pytorch_model-00004-of-00004.bin",
-    "model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.norm.weight": "pytorch_model-00004-of-00004.bin"
+    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.norm.weight": "pytorch_model-00003-of-00003.bin"
   }
 }