Upload folder using huggingface_hub

generation_config.json

@@ -1,6 +1,14 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 151643,
-  "eos_token_id": 151645,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
   "transformers_version": "4.51.3"
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1738358161d890d1bd38eb5a9fa522dd3805d254bab9420aae8980fdf2573d6
-size 4947356384
+oid sha256:4d152dd1a912bb4be52c57643bf2391907f19b5d12a3d11d3a4b40425ad2c1c9
+size 4962168672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc12675f88ab3604cfdcc75eced87491e33b554ba908d81dbd0cb3c2448219e7
-size 4958476976
+oid sha256:cbb573e1630fd2522a75b5e6225801b55c987f90dcee0dea6182e9ccb793bec9
+size 4983983776

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8e746619da1bdc8483477a2247183a2b5d460b02f090b7cce62b7f5cc30d7e6
-size 4998799224
+oid sha256:fc9b345bc1cf2cabb9cc8ed248152ce49c8d1bcbc6631990167cd72ccabbdac8
+size 4918063896

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:190635bc7a99ba2de0e36e3729a5e7a3242e8fa8d8d53273ea9afad7b2abe5a9
-size 326639312
+oid sha256:45da7fa7880b998efcd2afa16608d8847dec3347786644ed7a85cab0683b4406
+size 367055496

model.safetensors.index.json

@@ -3,344 +3,344 @@
     "total_size": 15231233024
   },
   "weight_map": {
-    "lm_head.weight": "model-00001-of-00004.safetensors",
+    "lm_head.weight": "model-00002-of-00004.safetensors",
     "model.embed_tokens.weight": "model-00003-of-00004.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.0.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
     "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
     "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.14.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.15.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
     "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
     "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.2.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.2.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
     "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
     "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
     "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
     "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
     "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.27.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.3.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
     "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.4.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.4.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.5.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.5.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
     "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.norm.weight": "model-00001-of-00004.safetensors"
+    "model.norm.weight": "model-00003-of-00004.safetensors"
   }
 }