Upload LlamaForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "lora-out/merged",
+  "_name_or_path": "/content/mymodel",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -22,8 +22,8 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.40.0.dev0",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0",
   "use_cache": false,
   "vocab_size": 128256
 }

generation_config.json

@@ -4,5 +4,5 @@
   "do_sample": true,
   "eos_token_id": 2,
   "pad_token_id": 2,
-  "transformers_version": "4.40.0.dev0"
+  "transformers_version": "4.40.0"
 }

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d9e86dc14f7327a27a488993c41e6bbc926e26468b63f4c1f7705091b1028c2
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfde1a7bc32cdc3236ff3481994d2b58872e9a7292c0fea18601f3ab6d7a34ae
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4e60f82ed04543ad142f6e9f68d14389914869e8058b6130c47af7aafc09cec
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a290ab6c8e8f2799794a1d303f1b6be9019faaa0df157e09c76a0f1bb41bc4d4
+size 1168138808

model.safetensors.index.json

@@ -1,298 +1,298 @@
 {
   "metadata": {
-    "total_size": 32121044992
+    "total_size": 16060522496
   },
   "weight_map": {
-    "lm_head.weight": "model-00007-of-00007.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.norm.weight": "model-00007-of-00007.safetensors"
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
   }
 }