Upload LlamaForCausalLM

config.json

@@ -1,7 +1,7 @@
 {
   "_name_or_path": "/JawTitan/magicoder/magicoder-ds",
   "architectures": [
-    "LlamaModel"
+    "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 32013,
+  "eos_token_id": 32014,
+  "transformers_version": "4.36.0.dev0"
+}

model-00001-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f5712e8474977a572480885fda1c9202eea6d5380fb18f18503adc9d1f24239
-size 4844590416
+oid sha256:e2c00355771f8fe2fdeeac28c008137c5754f485aa6515657da3288a0064afc7
+size 4844590720

model-00002-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20eb7baeb5c96c9469924802c6f20852d80d3a2859d807eab1e6eebbd5033ce7
-size 4857206528
+oid sha256:8af1e61356b29150f74ab7114d55370df28096449b83b2d612fb66d02df1a2fd
+size 4857206856

model-00003-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5ca006d066e638bf2fcb3233064c70988c86652465fea7026a6c271c01809c6
-size 4857206576
+oid sha256:687627af2da107164ebd9e02aed377dbdc407e6efcb1bc490e05706bf79a4d42
+size 4857206904

model-00004-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64206024aa4d7fb64edd728fb5daac7e05c0a39772036579bcaf2e25efd0e941
-size 4857206576
+oid sha256:e0a121ef15881c70919c24a256c33facf63ee410614151bea99be66d1b71ac29
+size 4857206904

model-00005-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50e9c23d288b88015dccb3e6b7140d4f5677a422c3a1c5f81baeebd69e655465
-size 4857206576
+oid sha256:918f6f1c1e3fa46e58c7b4364f7e84198c21895565b9790bc6794e6b1a90dfe1
+size 4857206904

model-00006-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d91d6e0a74a3ce450064575ba7ad115dbb287ae679f4f5be90b9ce7ccab6b41
-size 2160183864
+oid sha256:38882367e1d5baf023deeacf74dd4683f216c5503c2772d4968797e94debdb93
+size 2688666416

model.safetensors.index.json

@@ -1,297 +1,298 @@
 {
   "metadata": {
-    "total_size": 26433568768
+    "total_size": 26962051072
   },
   "weight_map": {
-    "embed_tokens.weight": "model-00001-of-00006.safetensors",
-    "layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "norm.weight": "model-00006-of-00006.safetensors"
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
   }
 }