Upload folder using huggingface_hub

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b87c52af543a90425d40f0b505302d798d87715b38ef9c132c57d8bb7029c84
-size 4980519768
+oid sha256:7ce69791343d67f80d18ba0e5304790ecb57608d4bb122e2ccba61c27d7884b3
+size 4954808184

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dd8c92ca581abe355371b58ddba5a5846d7cebda9381635943ce71ae34cb806
-size 4910709072
+oid sha256:a90509f996354cc4dd14b5bcabdac7a340c383ad7b7fbd59958926d5acfff16f
+size 4947417640

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d10602edb28ba72cbe7bfe767aec27a71a3e1c1e1be235ba8eca2d56392d0570
-size 4987691640
+oid sha256:d4f9479ad35269a8b28c06d969879e179be97d279b138db7b1b227214eb29451
+size 4921673952

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fdf2842dd590964320698299765073fc1d709b378b733c303d10714587e9f32
-size 352351400
+oid sha256:7746c95e6602dcdbe2cc9678eb06171b44c130f3c2ee1d208e3da0dd88af6eeb
+size 407372152

model.safetensors.index.json

@@ -5,342 +5,342 @@
   "weight_map": {
     "lm_head.weight": "model-00002-of-00004.safetensors",
     "model.embed_tokens.weight": "model-00003-of-00004.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.k_proj.bias": "model-00002-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-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-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-00001-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-00001-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.1.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.mlp.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.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.k_proj.bias": "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-00002-of-00004.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00004-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-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.10.post_attention_layernorm.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-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-00002-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-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.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-00003-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.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00001-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-00001-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-00002-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-00002-of-00004.safetensors",
     "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.11.mlp.up_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-00001-of-00004.safetensors",
-    "model.layers.11.self_attn.k_proj.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-00001-of-00004.safetensors",
     "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.11.self_attn.v_proj.bias": "model-00003-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-00002-of-00004.safetensors",
     "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.12.mlp.down_proj.weight": "model-00001-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-00003-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-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.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-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-00004-of-00004.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00004-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-00002-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.13.mlp.down_proj.weight": "model-00002-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-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-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-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-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.14.mlp.gate_proj.weight": "model-00002-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-00002-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-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-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-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-00001-of-00004.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.14.self_attn.v_proj.bias": "model-00001-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-00003-of-00004.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00004-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-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-00002-of-00004.safetensors",
-    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00002-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.16.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.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-00001-of-00004.safetensors",
-    "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
     "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.16.self_attn.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.bias": "model-00003-of-00004.safetensors",
     "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.17.input_layernorm.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-00003-of-00004.safetensors",
     "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.k_proj.bias": "model-00001-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-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.o_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-00001-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-00003-of-00004.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00002-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-00001-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-00004-of-00004.safetensors",
     "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.18.mlp.up_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-00001-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-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-00001-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-00001-of-00004.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-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-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.mlp.gate_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.post_attention_layernorm.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-00001-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.q_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-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-00001-of-00004.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00004-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-00002-of-00004.safetensors",
     "model.layers.2.input_layernorm.weight": "model-00002-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.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.2.mlp.up_proj.weight": "model-00001-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.k_proj.weight": "model-00001-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-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.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-00001-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-00003-of-00004.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
     "model.layers.20.self_attn.k_proj.weight": "model-00002-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.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-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.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-00001-of-00004.safetensors",
     "model.layers.21.post_attention_layernorm.weight": "model-00001-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-00001-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
     "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "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-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.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-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-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-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
     "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.22.self_attn.o_proj.weight": "model-00001-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-00001-of-00004.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-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.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00004-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-00001-of-00004.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
     "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.self_attn.v_proj.bias": "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-00002-of-00004.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.24.mlp.gate_proj.weight": "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-00003-of-00004.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00002-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-00003-of-00004.safetensors",
     "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00001-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-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-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-00003-of-00004.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00004-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-00002-of-00004.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.q_proj.bias": "model-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-00001-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-00002-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-00001-of-00004.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00001-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-00003-of-00004.safetensors",
     "model.layers.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-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-00002-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-00001-of-00004.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00001-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-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-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-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-00004-of-00004.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.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-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-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-00003-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-00003-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.3.self_attn.k_proj.weight": "model-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-00002-of-00004.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.3.self_attn.v_proj.bias": "model-00002-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-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
     "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00003-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-00001-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-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.q_proj.bias": "model-00003-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-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-00003-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-00002-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-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-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-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-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-00002-of-00004.safetensors",
-    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.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.v_proj.bias": "model-00001-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-00002-of-00004.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00003-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.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-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-00001-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-00002-of-00004.safetensors",
-    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00002-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-00003-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-00002-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.mlp.down_proj.weight": "model-00003-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-00003-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-00004-of-00004.safetensors",
-    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00001-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-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-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-00002-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-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-00003-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
     "model.layers.8.self_attn.k_proj.weight": "model-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-00003-of-00004.safetensors",
-    "model.layers.8.self_attn.q_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.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.v_proj.bias": "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-00003-of-00004.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "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-00001-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-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.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-00003-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-00002-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-00002-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-00003-of-00004.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.norm.weight": "model-00003-of-00004.safetensors"
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00001-of-00004.safetensors"
   }
 }