Upload folder using huggingface_hub

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:553d3baff5c234dbf3666ab901698ca1850ef0fefb6c9bb172458d3225ac68ca
-size 4991411456
+oid sha256:2e8b5f8e63271438e2348d93160f695f3f7d9e4a556eb71802e7561078473cc4
+size 4998741256

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dff68df48616fea1896419349ea08ff044015a85d4841439d367e7e6eb3459f
-size 4954692552
+oid sha256:80c155c3f878a470de090093df4f27d24f3ad5e8a4ae01c4a198ee9349b3061e
+size 4980376208

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e8b6bc8c08887e0fe8cb1a7425761684050723e0431f9f6e4ced18cfdd88e26
-size 4958521304
+oid sha256:60bfbfa562daf77a6e5279d5d6dd95241c8ecf2c8db356a90463e3ffefbe857e
+size 4976895560

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:386f0663319226b63c791e3ff979266af5c65c5e7c177a60f30ff37fc57b8736
-size 326646576
+oid sha256:0265211ad7f9c8c75ada0fc139e6fa15cf9b16a9f99edbd2283c0662b74adbbb
+size 275258840

model.safetensors.index.json

@@ -6,338 +6,338 @@
     "lm_head.weight": "model-00001-of-00004.safetensors",
     "model.embed_tokens.weight": "model-00002-of-00004.safetensors",
     "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-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-00003-of-00004.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "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-00002-of-00004.safetensors",
     "model.layers.0.self_attn.q_proj.bias": "model-00002-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-00003-of-00004.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00003-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-00003-of-00004.safetensors",
     "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.1.mlp.down_proj.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-00001-of-00004.safetensors",
     "model.layers.1.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.1.post_attention_layernorm.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-00003-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-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-00003-of-00004.safetensors",
-    "model.layers.1.self_attn.v_proj.bias": "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.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-00001-of-00004.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-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-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-00004-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-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-00003-of-00004.safetensors",
-    "model.layers.11.mlp.gate_proj.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-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-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-00001-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-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.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-00003-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-00002-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-00001-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-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-00002-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-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-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-00003-of-00004.safetensors",
     "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.12.self_attn.k_proj.bias": "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.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-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-00001-of-00004.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.13.post_attention_layernorm.weight": "model-00001-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-00002-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-00001-of-00004.safetensors",
-    "model.layers.13.self_attn.v_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-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-00003-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
     "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.mlp.down_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-00003-of-00004.safetensors",
     "model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.k_proj.bias": "model-00001-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-00003-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.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.q_proj.weight": "model-00003-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-00001-of-00004.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.mlp.gate_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-00004-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.15.self_attn.k_proj.bias": "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.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-00003-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-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-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-00003-of-00004.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-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.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.17.input_layernorm.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.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00001-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-00003-of-00004.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-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-00004-of-00004.safetensors",
-    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-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-00001-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.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "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-00003-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-00001-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-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-00003-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-00001-of-00004.safetensors",
+    "model.layers.18.self_attn.q_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-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.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-00001-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.post_attention_layernorm.weight": "model-00001-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-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.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
     "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.2.input_layernorm.weight": "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-00003-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.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00003-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-00003-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-00001-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-00001-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.2.self_attn.o_proj.weight": "model-00002-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-00001-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-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.20.self_attn.k_proj.bias": "model-00002-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-00003-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-00001-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-00001-of-00004.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00002-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.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00002-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-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-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-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.q_proj.bias": "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-00003-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-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-00001-of-00004.safetensors",
     "model.layers.22.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.self_attn.k_proj.bias": "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-00002-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-00003-of-00004.safetensors",
-    "model.layers.22.self_attn.o_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-00003-of-00004.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "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-00002-of-00004.safetensors",
     "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.input_layernorm.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-00003-of-00004.safetensors",
-    "model.layers.23.mlp.up_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-00002-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.post_attention_layernorm.weight": "model-00003-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-00001-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-00001-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-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-00002-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.v_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.self_attn.k_proj.bias": "model-00001-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-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-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-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-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-00003-of-00004.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.input_layernorm.weight": "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-00001-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-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.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-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-00003-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-00003-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.v_proj.bias": "model-00002-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.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.26.mlp.down_proj.weight": "model-00003-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.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-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-00002-of-00004.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00003-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-00001-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.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-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-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00003-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-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-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-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-00002-of-00004.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "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-00003-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.3.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-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-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00002-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-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.v_proj.weight": "model-00001-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.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.4.mlp.gate_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.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.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-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-00002-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-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.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-00003-of-00004.safetensors",
     "model.layers.5.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.5.post_attention_layernorm.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-00003-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-00002-of-00004.safetensors",
-    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-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-00001-of-00004.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.mlp.down_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-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-00002-of-00004.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.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-00001-of-00004.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00002-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-00003-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-00003-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-00001-of-00004.safetensors",
     "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.7.mlp.gate_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-00003-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.k_proj.bias": "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-00002-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-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-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.8.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "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-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00002-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-00001-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-00001-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-00001-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-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00003-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-00003-of-00004.safetensors",
     "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00001-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.gate_proj.weight": "model-00003-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-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00001-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-00002-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-00003-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
     "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
     "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",