Upload folder using huggingface_hub

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2d7d49b934fdb6c28f9439d3ea92b91d11a8cd75b6356d3b84f2c1f0234f9de
-size 4991475776
+oid sha256:2bfafa936bee9eb26aa4aa5cbf28915ab8a48f5247b446346ddea8a27a925a5f
+size 4572993208

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb10672bc2a1672134e7d27bac84186c268387a0c61a63a94750d390ea6112b6
-size 4606173824
+oid sha256:9820cc3f22315c107fcd56e7b0316df55cab3026938c84d9f499b5573ab04589
+size 4958409824

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e12c68ec68f18c33a47221f52ecabd29b51d7fe3b41c6466b974740ed693a50c
-size 4870211768
+oid sha256:7055e7503d745a6a1f66aa0a394772bb70c62658c57eded74f4e879f9d8ee7b7
+size 4910768128

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d97b934b54e34d72adda184a684bda786fae8470ea1a9c825086d65136166169
-size 763410432
+oid sha256:b1b608122c3f5aa8c1e4ac1d0883f64b3da945e85ff1fdbcba2be42a1cb793eb
+size 789100672

model.safetensors.index.json

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