Trained with Unsloth

README.md

@@ -8,6 +8,7 @@ tags:
 - unsloth
 - llama
 - trl
+- sft
 base_model: unsloth/llama-3-8b-bnb-4bit
 ---
 

config.json

@@ -16,7 +16,6 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
-  "pad_token_id": 128001,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8361228c928e21e0214aff20220b145c3c1c9b90fb3b3d7bf933907ef84d6f5c
+oid sha256:197ca6dc1b1f62c7e0589ee2a751849879fca0de46a583ff451d434b9a84ae50
 size 4976698592

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed313514e7ab04aeb9aa14123d104e9b8f77cc1317f6ed6a6b6395575e16afc0
+oid sha256:9d125886fa9c767fd283d676886b514675594dcafa06dc0c1d4aaf3ab6a5ec6f
 size 4999802616

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4faa983b29ad78b3847bab68cca127a76a3961b69855d19b98653ffbc0ad68c4
+oid sha256:d4a54cc44a9c1780789f559c811c4b6672b8a8f5aff5db9d4a0ff69c40236bee
 size 4915916080

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5873d77207c8e6a28e89ebaccf4b7945a9dc8ab76a43fd2c83a4279005216996
+oid sha256:b3b971f4e54f9cbd4af767dbcac40d6c18183ac8d1ce59f11653e723a595b265
 size 1168138808

model.safetensors.index.json

@@ -1,298 +1,298 @@
 {
-    "metadata": {
-        "total_size": 16060522496
-    },
-    "weight_map": {
-        "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"
-    }
-}
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "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"
+  }
+}