use 6 shards instead of 2

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "codellama/CodeLlama-7b-Instruct-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -18,8 +19,8 @@
   "rope_scaling": null,
   "rope_theta": 1000000,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.32.0.dev0",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.0.dev0",
   "use_cache": true,
   "vocab_size": 32016
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.32.0.dev0"
+  "transformers_version": "4.33.0.dev0"
 }

pytorch_model-00001-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4e715bd18d72fbb7c6ecfc2bfbe20e94f15b485728b2b5203a4592781d703bb
+size 4840669603

pytorch_model-00002-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06915b957e6b6485d01bf50982d204827901bb0021de96c0acdcedcdeb0c7e3d
+size 4857218807

pytorch_model-00003-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:976d878e931d5f109f5445fc48c3522abee8b83fcede561ae9e6e1ce01c1d955
+size 4857218807

pytorch_model-00004-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0df4a45658f3c2c8024fa469df8d050c0605e38a3b6f46720606309f9f800587
+size 4857218807

pytorch_model-00005-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06eb91468aa4aa60ee1466d56823517f3b1e92ecd9a6351a06af5d0b5aee30a4
+size 4857218807

pytorch_model-00006-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d56f21a4e0dc163f956e30f27a0bdf85cdf08c7a79cc0516ec50554af07932ee
+size 2684739793

pytorch_model.bin.index.json

@@ -1,298 +1,298 @@
 {
   "metadata": {
-    "total_size": 13477093376
+    "total_size": 26954186752
   },
   "weight_map": {
-    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
-    "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.norm.weight": "pytorch_model-00002-of-00002.bin"
+    "lm_head.weight": "pytorch_model-00006-of-00006.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.norm.weight": "pytorch_model-00006-of-00006.bin"
   }
 }