finetuned

config.json

@@ -21,7 +21,7 @@
   "rope_scaling": null,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.40.0",
   "use_cache": true,
   "vocab_size": 145088

model-00001-of-00007.safetensors → model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83ce27eb64d42331dc895aacb10817d6e0f3a421efac7d8b8fa7e58d677f39a5
-size 4994469032
+oid sha256:57b6a8c0afd3e9c52c7893d026454d0f838fe279c75aadd7bfba3434f35b9223
+size 4997129176

model-00002-of-00007.safetensors → model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8369130d2e30bee6863dde401ca24a831aa2f60ecfa29e24c2b5fec507a80d30
-size 4999780072
+oid sha256:946fbb66c65ce624c20853b329366b37d3014eee9d3242c45a9e1728b256760c
+size 4999819328

model-00003-of-00007.safetensors → model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f66fe1664f2f9b0b16656dc50283106106c844662a05e469e2a444dad4cda0f7
-size 4999813112
+oid sha256:fdb386f789b7c3844163771d0eb566a86c0d528fd98f2ebaddaf99c180adf67a
+size 4915916184

model-00004-of-00007.safetensors → model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d656a236cadaeb707f399c4247a9ef89c5d8663fabbb2d67e42431049855bbfa
-size 4999813128
+oid sha256:fab99e1cffc15f8e45da503965501651b6a3b28a021e772e6133e0abcff596c2
+size 1423467176

model-00005-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6fc87d22889ebec02d0bb8ffa1534a416fab5a12a7d203827696dae0aaaf370a
-size 4832007496

model-00006-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e61e1f94a378dc014786bc1b9ea9c1af246560bce2cc387e23c7fd1cca2d7828
-size 4999813120

model-00007-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:691ba9875a88febdf45d58dfcef6d68c6740950a5a6a184e04472cbab9ef1afa
-size 2846933672

model.safetensors.index.json

@@ -1,298 +1,298 @@
 {
   "metadata": {
-    "total_size": 32672595968
+    "total_size": 16336297984
   },
   "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-00002-of-00007.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00002-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-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.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-00004-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-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-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-00002-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"
   }
 }