Adding `safetensors` variant of this model

model-00001-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0b62ab44c24ddd6e233c73911becd96b597c60d9db3c0c3a678901bbad4c95a
+size 4548798728

model-00002-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:220628bce168051d08168930a88535f93d4da8b32ef383eefd0268ecc8f333a2
+size 4964101384

model-00003-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11f450854665e378dc326743f2bb082f7d2834b4c8aeb87c8ba5feb82935301c
+size 4781637328

model-00004-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c31d02ba6b4665206c2d12a746b8fc501a02f80e6d111a8468d3a4aea036a2ab
+size 4781670320

model-00005-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:affe768a4ec949fb0d6fd431cb53162b4b6e26984c3bf58830c1d96d280bc300
+size 4781670360

model-00006-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90b0e8452774bd8ccc9bc0038fe6af56957c87eaed6d1ef6e698d98d3eb5c79e
+size 4964101416

model-00007-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26cb82a9dce9b7f1d2c5762d280f5cac4d4a5f5409695ba078e9bdb25660fe86
+size 4781637360

model-00008-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a466b638d372f7eb49db75a32e9b5d7319e16e033eef5247729eefb0a9a42cc
+size 4781670360

model-00009-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eefc344331b708d8b2f6df6e46788f46e87541612aef7e6051770b3be4b85290
+size 4781670360

model-00010-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d407fcbe63d99b884e254b928aca28a4be4bda684b5cf13e62de0bc53090c1fb
+size 4964101416

model-00011-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1abb162b70e144efaf71c8ed8dadf4679a4719df1a49994c280a27969b52caa
+size 4781637360

model-00012-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:286ec72ec598b47d2461ff9d830a0b297e1301008f7aa1435e595bab2787f31a
+size 4781670360

model-00013-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c80c59bbe1970da390ef37bdd90b8e2ecc1840a111d703443ec30d7f6bc75d48
+size 4781670360

model-00014-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e93d1f021c67cb8a110a6860e8f235d02bc8fb36a92f679518f0f23b8564a679
+size 4964101416

model-00015-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e29d0c9e862b15eb6628ff600c85bb0f1f8824adabe383b6a452ddb323a2ca7
+size 4781637360

model-00016-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e86b1f50a7449996af4375e7e41195594b4cd908964f9596850697929d7d2ea
+size 4781670360

model-00017-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d5a88eb5197957eadff41ae3c5d6aa6e9f1ea25ecdaaf2e81e381d800f1294e
+size 4781670360

model-00018-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bf07cb5a2bf2b861aca929df41729081c921dae65ae14aff5733bfdb9832075
+size 4964101416

model-00019-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56ec5ca1a4f33a862699223e62ab068aeb9af24fba01168f2e11c0007c7f8187
+size 4781637360

model-00020-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e711ce551b43096039718cb41037535c5561dedbbd0bece5a3f3b2fa188a4907
+size 4781670360

model-00021-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:605e22743c89303e094f1b722118a9b79b7a499cd44e6f188ba912de8cd24071
+size 4781670360

model-00022-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee59ae4cbfb4299f7276d692ea3bf4105536ed5cf4d894b04e0e91cdbfd3e909
+size 4964101416

model-00023-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74f81e71a3ab384ab811056da84c3a51b323a6fa4beb487d12b25f4df7b26904
+size 4781637360

model-00024-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ca837a56945a80ae325a8777c4eba16eda2d3bbda2ab0c331faeedb6ed065b5
+size 4781670360

model-00025-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1bdb8d636e652a90f92b1bc559ecee3184060d334032d237767b27cc4f63d84
+size 4781670360

model-00026-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc3023df71b8bc394790d3e7c75b3a16881c586b17c0ea5d3e53977d642e9ea7
+size 4964101416

model-00027-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26fd3594b73981635f23bc504a62db29f8d8c4949127128f422376ac4a49cd71
+size 4781637360

model-00028-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d5552810c0da8aa12512a75ba420b5fb524bbc8e6c245af689bda6e3dd2fe4a
+size 4781670360

model-00029-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f192fa8560180a69334a0b364d12cf9204b6c289c372f61bea91a464547531a
+size 4781670360

model-00030-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:accecc0afc2863ded97e81e0b72f1fecd33d55699befd29befb9f9e19df0c8e4
+size 3208747032

model-00031-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:974ad7a256e1c96f44d544d73b4381b8ad95ffcde52c6c0e1840e83ca87f109d
+size 2491416704

model.safetensors.index.json

@@ -0,0 +1,970 @@
+{
+    "metadata": {
+        "total_size": 145412407296
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00031-of-00031.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00031.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00031.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00031.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00031.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00031.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00031.safetensors",
+        "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00031.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00031.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00031.safetensors",
+        "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00031.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00031.safetensors",
+        "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00031.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00031.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00002-of-00031.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00002-of-00031.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00031.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00002-of-00031.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00031.safetensors",
+        "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00031.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00031.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00031.safetensors",
+        "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00031.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00031.safetensors",
+        "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00031.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00031.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00005-of-00031.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00005-of-00031.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00031.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00005-of-00031.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00031.safetensors",
+        "model.layers.10.self_attn.k_proj.bias": "model-00005-of-00031.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00031.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00031.safetensors",
+        "model.layers.10.self_attn.q_proj.bias": "model-00005-of-00031.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00031.safetensors",
+        "model.layers.10.self_attn.v_proj.bias": "model-00005-of-00031.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00031.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00005-of-00031.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00005-of-00031.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00031.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00005-of-00031.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00031.safetensors",
+        "model.layers.11.self_attn.k_proj.bias": "model-00005-of-00031.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00031.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00031.safetensors",
+        "model.layers.11.self_attn.q_proj.bias": "model-00005-of-00031.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00031.safetensors",
+        "model.layers.11.self_attn.v_proj.bias": "model-00005-of-00031.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00031.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00006-of-00031.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00006-of-00031.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00031.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00006-of-00031.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00031.safetensors",
+        "model.layers.12.self_attn.k_proj.bias": "model-00005-of-00031.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00031.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00031.safetensors",
+        "model.layers.12.self_attn.q_proj.bias": "model-00005-of-00031.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00031.safetensors",
+        "model.layers.12.self_attn.v_proj.bias": "model-00005-of-00031.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00031.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00006-of-00031.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00006-of-00031.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00031.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00006-of-00031.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00031.safetensors",
+        "model.layers.13.self_attn.k_proj.bias": "model-00006-of-00031.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00031.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00031.safetensors",
+        "model.layers.13.self_attn.q_proj.bias": "model-00006-of-00031.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00031.safetensors",
+        "model.layers.13.self_attn.v_proj.bias": "model-00006-of-00031.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00031.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00006-of-00031.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00006-of-00031.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00031.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00006-of-00031.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00031.safetensors",
+        "model.layers.14.self_attn.k_proj.bias": "model-00006-of-00031.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00031.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00031.safetensors",
+        "model.layers.14.self_attn.q_proj.bias": "model-00006-of-00031.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00031.safetensors",
+        "model.layers.14.self_attn.v_proj.bias": "model-00006-of-00031.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00031.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00007-of-00031.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00007-of-00031.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00031.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00007-of-00031.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00031.safetensors",
+        "model.layers.15.self_attn.k_proj.bias": "model-00007-of-00031.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00031.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00031.safetensors",
+        "model.layers.15.self_attn.q_proj.bias": "model-00007-of-00031.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00031.safetensors",
+        "model.layers.15.self_attn.v_proj.bias": "model-00007-of-00031.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00031.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00007-of-00031.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00007-of-00031.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00031.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00007-of-00031.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00031.safetensors",
+        "model.layers.16.self_attn.k_proj.bias": "model-00007-of-00031.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00031.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00031.safetensors",
+        "model.layers.16.self_attn.q_proj.bias": "model-00007-of-00031.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00031.safetensors",
+        "model.layers.16.self_attn.v_proj.bias": "model-00007-of-00031.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00031.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00008-of-00031.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00008-of-00031.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00031.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00007-of-00031.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00031.safetensors",
+        "model.layers.17.self_attn.k_proj.bias": "model-00007-of-00031.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00031.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00031.safetensors",
+        "model.layers.17.self_attn.q_proj.bias": "model-00007-of-00031.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00031.safetensors",
+        "model.layers.17.self_attn.v_proj.bias": "model-00007-of-00031.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00031.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00008-of-00031.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00008-of-00031.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00031.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00008-of-00031.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00031.safetensors",
+        "model.layers.18.self_attn.k_proj.bias": "model-00008-of-00031.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00031.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00031.safetensors",
+        "model.layers.18.self_attn.q_proj.bias": "model-00008-of-00031.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00031.safetensors",
+        "model.layers.18.self_attn.v_proj.bias": "model-00008-of-00031.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00031.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00008-of-00031.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00008-of-00031.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00031.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00008-of-00031.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00031.safetensors",
+        "model.layers.19.self_attn.k_proj.bias": "model-00008-of-00031.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00031.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00031.safetensors",
+        "model.layers.19.self_attn.q_proj.bias": "model-00008-of-00031.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00031.safetensors",
+        "model.layers.19.self_attn.v_proj.bias": "model-00008-of-00031.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00031.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00002-of-00031.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00002-of-00031.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00031.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00002-of-00031.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00031.safetensors",
+        "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00031.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00031.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00031.safetensors",
+        "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00031.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00031.safetensors",
+        "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00031.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00031.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00009-of-00031.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00009-of-00031.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00031.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00009-of-00031.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00031.safetensors",
+        "model.layers.20.self_attn.k_proj.bias": "model-00008-of-00031.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00031.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00031.safetensors",
+        "model.layers.20.self_attn.q_proj.bias": "model-00008-of-00031.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00031.safetensors",
+        "model.layers.20.self_attn.v_proj.bias": "model-00008-of-00031.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00031.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00009-of-00031.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00009-of-00031.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00031.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00009-of-00031.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00031.safetensors",
+        "model.layers.21.self_attn.k_proj.bias": "model-00009-of-00031.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00031.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00031.safetensors",
+        "model.layers.21.self_attn.q_proj.bias": "model-00009-of-00031.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00031.safetensors",
+        "model.layers.21.self_attn.v_proj.bias": "model-00009-of-00031.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00031.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00009-of-00031.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00009-of-00031.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00031.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00009-of-00031.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00031.safetensors",
+        "model.layers.22.self_attn.k_proj.bias": "model-00009-of-00031.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00031.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00031.safetensors",
+        "model.layers.22.self_attn.q_proj.bias": "model-00009-of-00031.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00031.safetensors",
+        "model.layers.22.self_attn.v_proj.bias": "model-00009-of-00031.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00031.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00010-of-00031.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00010-of-00031.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00010-of-00031.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00010-of-00031.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00031.safetensors",
+        "model.layers.23.self_attn.k_proj.bias": "model-00009-of-00031.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00031.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00031.safetensors",
+        "model.layers.23.self_attn.q_proj.bias": "model-00009-of-00031.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00031.safetensors",
+        "model.layers.23.self_attn.v_proj.bias": "model-00009-of-00031.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00031.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00010-of-00031.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00010-of-00031.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00010-of-00031.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00010-of-00031.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00031.safetensors",
+        "model.layers.24.self_attn.k_proj.bias": "model-00010-of-00031.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00031.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00031.safetensors",
+        "model.layers.24.self_attn.q_proj.bias": "model-00010-of-00031.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00031.safetensors",
+        "model.layers.24.self_attn.v_proj.bias": "model-00010-of-00031.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00031.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00010-of-00031.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00010-of-00031.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00031.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00010-of-00031.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00031.safetensors",
+        "model.layers.25.self_attn.k_proj.bias": "model-00010-of-00031.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00031.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00031.safetensors",
+        "model.layers.25.self_attn.q_proj.bias": "model-00010-of-00031.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00031.safetensors",
+        "model.layers.25.self_attn.v_proj.bias": "model-00010-of-00031.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00031.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00011-of-00031.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00011-of-00031.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00011-of-00031.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00011-of-00031.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00031.safetensors",
+        "model.layers.26.self_attn.k_proj.bias": "model-00011-of-00031.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00031.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00031.safetensors",
+        "model.layers.26.self_attn.q_proj.bias": "model-00011-of-00031.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00011-of-00031.safetensors",
+        "model.layers.26.self_attn.v_proj.bias": "model-00011-of-00031.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00011-of-00031.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00011-of-00031.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00011-of-00031.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00011-of-00031.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00011-of-00031.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00031.safetensors",
+        "model.layers.27.self_attn.k_proj.bias": "model-00011-of-00031.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00011-of-00031.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00031.safetensors",
+        "model.layers.27.self_attn.q_proj.bias": "model-00011-of-00031.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00011-of-00031.safetensors",
+        "model.layers.27.self_attn.v_proj.bias": "model-00011-of-00031.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00011-of-00031.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00012-of-00031.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00012-of-00031.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00031.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00011-of-00031.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00012-of-00031.safetensors",
+        "model.layers.28.self_attn.k_proj.bias": "model-00011-of-00031.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00031.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00031.safetensors",
+        "model.layers.28.self_attn.q_proj.bias": "model-00011-of-00031.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00031.safetensors",
+        "model.layers.28.self_attn.v_proj.bias": "model-00011-of-00031.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00031.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00012-of-00031.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00012-of-00031.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00012-of-00031.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00012-of-00031.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00012-of-00031.safetensors",
+        "model.layers.29.self_attn.k_proj.bias": "model-00012-of-00031.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00012-of-00031.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00012-of-00031.safetensors",
+        "model.layers.29.self_attn.q_proj.bias": "model-00012-of-00031.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00012-of-00031.safetensors",
+        "model.layers.29.self_attn.v_proj.bias": "model-00012-of-00031.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00012-of-00031.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00002-of-00031.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00002-of-00031.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00031.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00002-of-00031.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00031.safetensors",
+        "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00031.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00031.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00031.safetensors",
+        "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00031.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00031.safetensors",
+        "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00031.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00031.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00012-of-00031.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00012-of-00031.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00031.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00012-of-00031.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00031.safetensors",
+        "model.layers.30.self_attn.k_proj.bias": "model-00012-of-00031.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00031.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00031.safetensors",
+        "model.layers.30.self_attn.q_proj.bias": "model-00012-of-00031.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00031.safetensors",
+        "model.layers.30.self_attn.v_proj.bias": "model-00012-of-00031.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00031.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00013-of-00031.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00013-of-00031.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00031.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00013-of-00031.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00013-of-00031.safetensors",
+        "model.layers.31.self_attn.k_proj.bias": "model-00012-of-00031.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00031.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00031.safetensors",
+        "model.layers.31.self_attn.q_proj.bias": "model-00012-of-00031.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00031.safetensors",
+        "model.layers.31.self_attn.v_proj.bias": "model-00012-of-00031.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00031.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00013-of-00031.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00013-of-00031.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model-00013-of-00031.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model-00013-of-00031.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00031.safetensors",
+        "model.layers.32.self_attn.k_proj.bias": "model-00013-of-00031.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00013-of-00031.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00013-of-00031.safetensors",
+        "model.layers.32.self_attn.q_proj.bias": "model-00013-of-00031.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00013-of-00031.safetensors",
+        "model.layers.32.self_attn.v_proj.bias": "model-00013-of-00031.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00013-of-00031.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00013-of-00031.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00013-of-00031.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00031.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model-00013-of-00031.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00031.safetensors",
+        "model.layers.33.self_attn.k_proj.bias": "model-00013-of-00031.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00031.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00013-of-00031.safetensors",
+        "model.layers.33.self_attn.q_proj.bias": "model-00013-of-00031.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00031.safetensors",
+        "model.layers.33.self_attn.v_proj.bias": "model-00013-of-00031.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00031.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00014-of-00031.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model-00014-of-00031.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model-00014-of-00031.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model-00014-of-00031.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model-00014-of-00031.safetensors",
+        "model.layers.34.self_attn.k_proj.bias": "model-00013-of-00031.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00031.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00031.safetensors",
+        "model.layers.34.self_attn.q_proj.bias": "model-00013-of-00031.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00031.safetensors",
+        "model.layers.34.self_attn.v_proj.bias": "model-00013-of-00031.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00031.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00014-of-00031.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model-00014-of-00031.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model-00014-of-00031.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model-00014-of-00031.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model-00014-of-00031.safetensors",
+        "model.layers.35.self_attn.k_proj.bias": "model-00014-of-00031.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00014-of-00031.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00014-of-00031.safetensors",
+        "model.layers.35.self_attn.q_proj.bias": "model-00014-of-00031.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00014-of-00031.safetensors",
+        "model.layers.35.self_attn.v_proj.bias": "model-00014-of-00031.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00014-of-00031.safetensors",
+        "model.layers.36.input_layernorm.weight": "model-00014-of-00031.safetensors",
+        "model.layers.36.mlp.down_proj.weight": "model-00014-of-00031.safetensors",
+        "model.layers.36.mlp.gate_proj.weight": "model-00014-of-00031.safetensors",
+        "model.layers.36.mlp.up_proj.weight": "model-00014-of-00031.safetensors",
+        "model.layers.36.post_attention_layernorm.weight": "model-00014-of-00031.safetensors",
+        "model.layers.36.self_attn.k_proj.bias": "model-00014-of-00031.safetensors",
+        "model.layers.36.self_attn.k_proj.weight": "model-00014-of-00031.safetensors",
+        "model.layers.36.self_attn.o_proj.weight": "model-00014-of-00031.safetensors",
+        "model.layers.36.self_attn.q_proj.bias": "model-00014-of-00031.safetensors",
+        "model.layers.36.self_attn.q_proj.weight": "model-00014-of-00031.safetensors",
+        "model.layers.36.self_attn.v_proj.bias": "model-00014-of-00031.safetensors",
+        "model.layers.36.self_attn.v_proj.weight": "model-00014-of-00031.safetensors",
+        "model.layers.37.input_layernorm.weight": "model-00015-of-00031.safetensors",
+        "model.layers.37.mlp.down_proj.weight": "model-00015-of-00031.safetensors",
+        "model.layers.37.mlp.gate_proj.weight": "model-00015-of-00031.safetensors",
+        "model.layers.37.mlp.up_proj.weight": "model-00015-of-00031.safetensors",
+        "model.layers.37.post_attention_layernorm.weight": "model-00015-of-00031.safetensors",
+        "model.layers.37.self_attn.k_proj.bias": "model-00015-of-00031.safetensors",
+        "model.layers.37.self_attn.k_proj.weight": "model-00015-of-00031.safetensors",
+        "model.layers.37.self_attn.o_proj.weight": "model-00015-of-00031.safetensors",
+        "model.layers.37.self_attn.q_proj.bias": "model-00015-of-00031.safetensors",
+        "model.layers.37.self_attn.q_proj.weight": "model-00015-of-00031.safetensors",
+        "model.layers.37.self_attn.v_proj.bias": "model-00015-of-00031.safetensors",
+        "model.layers.37.self_attn.v_proj.weight": "model-00015-of-00031.safetensors",
+        "model.layers.38.input_layernorm.weight": "model-00015-of-00031.safetensors",
+        "model.layers.38.mlp.down_proj.weight": "model-00015-of-00031.safetensors",
+        "model.layers.38.mlp.gate_proj.weight": "model-00015-of-00031.safetensors",
+        "model.layers.38.mlp.up_proj.weight": "model-00015-of-00031.safetensors",
+        "model.layers.38.post_attention_layernorm.weight": "model-00015-of-00031.safetensors",
+        "model.layers.38.self_attn.k_proj.bias": "model-00015-of-00031.safetensors",
+        "model.layers.38.self_attn.k_proj.weight": "model-00015-of-00031.safetensors",
+        "model.layers.38.self_attn.o_proj.weight": "model-00015-of-00031.safetensors",
+        "model.layers.38.self_attn.q_proj.bias": "model-00015-of-00031.safetensors",
+        "model.layers.38.self_attn.q_proj.weight": "model-00015-of-00031.safetensors",
+        "model.layers.38.self_attn.v_proj.bias": "model-00015-of-00031.safetensors",
+        "model.layers.38.self_attn.v_proj.weight": "model-00015-of-00031.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00016-of-00031.safetensors",
+        "model.layers.39.mlp.down_proj.weight": "model-00016-of-00031.safetensors",
+        "model.layers.39.mlp.gate_proj.weight": "model-00015-of-00031.safetensors",
+        "model.layers.39.mlp.up_proj.weight": "model-00015-of-00031.safetensors",
+        "model.layers.39.post_attention_layernorm.weight": "model-00016-of-00031.safetensors",
+        "model.layers.39.self_attn.k_proj.bias": "model-00015-of-00031.safetensors",
+        "model.layers.39.self_attn.k_proj.weight": "model-00015-of-00031.safetensors",
+        "model.layers.39.self_attn.o_proj.weight": "model-00015-of-00031.safetensors",
+        "model.layers.39.self_attn.q_proj.bias": "model-00015-of-00031.safetensors",
+        "model.layers.39.self_attn.q_proj.weight": "model-00015-of-00031.safetensors",
+        "model.layers.39.self_attn.v_proj.bias": "model-00015-of-00031.safetensors",
+        "model.layers.39.self_attn.v_proj.weight": "model-00015-of-00031.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00003-of-00031.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00003-of-00031.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00031.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00003-of-00031.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00031.safetensors",
+        "model.layers.4.self_attn.k_proj.bias": "model-00003-of-00031.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00031.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00031.safetensors",
+        "model.layers.4.self_attn.q_proj.bias": "model-00003-of-00031.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00031.safetensors",
+        "model.layers.4.self_attn.v_proj.bias": "model-00003-of-00031.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00031.safetensors",
+        "model.layers.40.input_layernorm.weight": "model-00016-of-00031.safetensors",
+        "model.layers.40.mlp.down_proj.weight": "model-00016-of-00031.safetensors",
+        "model.layers.40.mlp.gate_proj.weight": "model-00016-of-00031.safetensors",
+        "model.layers.40.mlp.up_proj.weight": "model-00016-of-00031.safetensors",
+        "model.layers.40.post_attention_layernorm.weight": "model-00016-of-00031.safetensors",
+        "model.layers.40.self_attn.k_proj.bias": "model-00016-of-00031.safetensors",
+        "model.layers.40.self_attn.k_proj.weight": "model-00016-of-00031.safetensors",
+        "model.layers.40.self_attn.o_proj.weight": "model-00016-of-00031.safetensors",
+        "model.layers.40.self_attn.q_proj.bias": "model-00016-of-00031.safetensors",
+        "model.layers.40.self_attn.q_proj.weight": "model-00016-of-00031.safetensors",
+        "model.layers.40.self_attn.v_proj.bias": "model-00016-of-00031.safetensors",
+        "model.layers.40.self_attn.v_proj.weight": "model-00016-of-00031.safetensors",
+        "model.layers.41.input_layernorm.weight": "model-00016-of-00031.safetensors",
+        "model.layers.41.mlp.down_proj.weight": "model-00016-of-00031.safetensors",
+        "model.layers.41.mlp.gate_proj.weight": "model-00016-of-00031.safetensors",
+        "model.layers.41.mlp.up_proj.weight": "model-00016-of-00031.safetensors",
+        "model.layers.41.post_attention_layernorm.weight": "model-00016-of-00031.safetensors",
+        "model.layers.41.self_attn.k_proj.bias": "model-00016-of-00031.safetensors",
+        "model.layers.41.self_attn.k_proj.weight": "model-00016-of-00031.safetensors",
+        "model.layers.41.self_attn.o_proj.weight": "model-00016-of-00031.safetensors",
+        "model.layers.41.self_attn.q_proj.bias": "model-00016-of-00031.safetensors",
+        "model.layers.41.self_attn.q_proj.weight": "model-00016-of-00031.safetensors",
+        "model.layers.41.self_attn.v_proj.bias": "model-00016-of-00031.safetensors",
+        "model.layers.41.self_attn.v_proj.weight": "model-00016-of-00031.safetensors",
+        "model.layers.42.input_layernorm.weight": "model-00017-of-00031.safetensors",
+        "model.layers.42.mlp.down_proj.weight": "model-00017-of-00031.safetensors",
+        "model.layers.42.mlp.gate_proj.weight": "model-00016-of-00031.safetensors",
+        "model.layers.42.mlp.up_proj.weight": "model-00017-of-00031.safetensors",
+        "model.layers.42.post_attention_layernorm.weight": "model-00017-of-00031.safetensors",
+        "model.layers.42.self_attn.k_proj.bias": "model-00016-of-00031.safetensors",
+        "model.layers.42.self_attn.k_proj.weight": "model-00016-of-00031.safetensors",
+        "model.layers.42.self_attn.o_proj.weight": "model-00016-of-00031.safetensors",
+        "model.layers.42.self_attn.q_proj.bias": "model-00016-of-00031.safetensors",
+        "model.layers.42.self_attn.q_proj.weight": "model-00016-of-00031.safetensors",
+        "model.layers.42.self_attn.v_proj.bias": "model-00016-of-00031.safetensors",
+        "model.layers.42.self_attn.v_proj.weight": "model-00016-of-00031.safetensors",
+        "model.layers.43.input_layernorm.weight": "model-00017-of-00031.safetensors",
+        "model.layers.43.mlp.down_proj.weight": "model-00017-of-00031.safetensors",
+        "model.layers.43.mlp.gate_proj.weight": "model-00017-of-00031.safetensors",
+        "model.layers.43.mlp.up_proj.weight": "model-00017-of-00031.safetensors",
+        "model.layers.43.post_attention_layernorm.weight": "model-00017-of-00031.safetensors",
+        "model.layers.43.self_attn.k_proj.bias": "model-00017-of-00031.safetensors",
+        "model.layers.43.self_attn.k_proj.weight": "model-00017-of-00031.safetensors",
+        "model.layers.43.self_attn.o_proj.weight": "model-00017-of-00031.safetensors",
+        "model.layers.43.self_attn.q_proj.bias": "model-00017-of-00031.safetensors",
+        "model.layers.43.self_attn.q_proj.weight": "model-00017-of-00031.safetensors",
+        "model.layers.43.self_attn.v_proj.bias": "model-00017-of-00031.safetensors",
+        "model.layers.43.self_attn.v_proj.weight": "model-00017-of-00031.safetensors",
+        "model.layers.44.input_layernorm.weight": "model-00017-of-00031.safetensors",
+        "model.layers.44.mlp.down_proj.weight": "model-00017-of-00031.safetensors",
+        "model.layers.44.mlp.gate_proj.weight": "model-00017-of-00031.safetensors",
+        "model.layers.44.mlp.up_proj.weight": "model-00017-of-00031.safetensors",
+        "model.layers.44.post_attention_layernorm.weight": "model-00017-of-00031.safetensors",
+        "model.layers.44.self_attn.k_proj.bias": "model-00017-of-00031.safetensors",
+        "model.layers.44.self_attn.k_proj.weight": "model-00017-of-00031.safetensors",
+        "model.layers.44.self_attn.o_proj.weight": "model-00017-of-00031.safetensors",
+        "model.layers.44.self_attn.q_proj.bias": "model-00017-of-00031.safetensors",
+        "model.layers.44.self_attn.q_proj.weight": "model-00017-of-00031.safetensors",
+        "model.layers.44.self_attn.v_proj.bias": "model-00017-of-00031.safetensors",
+        "model.layers.44.self_attn.v_proj.weight": "model-00017-of-00031.safetensors",
+        "model.layers.45.input_layernorm.weight": "model-00018-of-00031.safetensors",
+        "model.layers.45.mlp.down_proj.weight": "model-00018-of-00031.safetensors",
+        "model.layers.45.mlp.gate_proj.weight": "model-00018-of-00031.safetensors",
+        "model.layers.45.mlp.up_proj.weight": "model-00018-of-00031.safetensors",
+        "model.layers.45.post_attention_layernorm.weight": "model-00018-of-00031.safetensors",
+        "model.layers.45.self_attn.k_proj.bias": "model-00017-of-00031.safetensors",
+        "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00031.safetensors",
+        "model.layers.45.self_attn.o_proj.weight": "model-00017-of-00031.safetensors",
+        "model.layers.45.self_attn.q_proj.bias": "model-00017-of-00031.safetensors",
+        "model.layers.45.self_attn.q_proj.weight": "model-00017-of-00031.safetensors",
+        "model.layers.45.self_attn.v_proj.bias": "model-00017-of-00031.safetensors",
+        "model.layers.45.self_attn.v_proj.weight": "model-00017-of-00031.safetensors",
+        "model.layers.46.input_layernorm.weight": "model-00018-of-00031.safetensors",
+        "model.layers.46.mlp.down_proj.weight": "model-00018-of-00031.safetensors",
+        "model.layers.46.mlp.gate_proj.weight": "model-00018-of-00031.safetensors",
+        "model.layers.46.mlp.up_proj.weight": "model-00018-of-00031.safetensors",
+        "model.layers.46.post_attention_layernorm.weight": "model-00018-of-00031.safetensors",
+        "model.layers.46.self_attn.k_proj.bias": "model-00018-of-00031.safetensors",
+        "model.layers.46.self_attn.k_proj.weight": "model-00018-of-00031.safetensors",
+        "model.layers.46.self_attn.o_proj.weight": "model-00018-of-00031.safetensors",
+        "model.layers.46.self_attn.q_proj.bias": "model-00018-of-00031.safetensors",
+        "model.layers.46.self_attn.q_proj.weight": "model-00018-of-00031.safetensors",
+        "model.layers.46.self_attn.v_proj.bias": "model-00018-of-00031.safetensors",
+        "model.layers.46.self_attn.v_proj.weight": "model-00018-of-00031.safetensors",
+        "model.layers.47.input_layernorm.weight": "model-00018-of-00031.safetensors",
+        "model.layers.47.mlp.down_proj.weight": "model-00018-of-00031.safetensors",
+        "model.layers.47.mlp.gate_proj.weight": "model-00018-of-00031.safetensors",
+        "model.layers.47.mlp.up_proj.weight": "model-00018-of-00031.safetensors",
+        "model.layers.47.post_attention_layernorm.weight": "model-00018-of-00031.safetensors",
+        "model.layers.47.self_attn.k_proj.bias": "model-00018-of-00031.safetensors",
+        "model.layers.47.self_attn.k_proj.weight": "model-00018-of-00031.safetensors",
+        "model.layers.47.self_attn.o_proj.weight": "model-00018-of-00031.safetensors",
+        "model.layers.47.self_attn.q_proj.bias": "model-00018-of-00031.safetensors",
+        "model.layers.47.self_attn.q_proj.weight": "model-00018-of-00031.safetensors",
+        "model.layers.47.self_attn.v_proj.bias": "model-00018-of-00031.safetensors",
+        "model.layers.47.self_attn.v_proj.weight": "model-00018-of-00031.safetensors",
+        "model.layers.48.input_layernorm.weight": "model-00019-of-00031.safetensors",
+        "model.layers.48.mlp.down_proj.weight": "model-00019-of-00031.safetensors",
+        "model.layers.48.mlp.gate_proj.weight": "model-00019-of-00031.safetensors",
+        "model.layers.48.mlp.up_proj.weight": "model-00019-of-00031.safetensors",
+        "model.layers.48.post_attention_layernorm.weight": "model-00019-of-00031.safetensors",
+        "model.layers.48.self_attn.k_proj.bias": "model-00019-of-00031.safetensors",
+        "model.layers.48.self_attn.k_proj.weight": "model-00019-of-00031.safetensors",
+        "model.layers.48.self_attn.o_proj.weight": "model-00019-of-00031.safetensors",
+        "model.layers.48.self_attn.q_proj.bias": "model-00019-of-00031.safetensors",
+        "model.layers.48.self_attn.q_proj.weight": "model-00019-of-00031.safetensors",
+        "model.layers.48.self_attn.v_proj.bias": "model-00019-of-00031.safetensors",
+        "model.layers.48.self_attn.v_proj.weight": "model-00019-of-00031.safetensors",
+        "model.layers.49.input_layernorm.weight": "model-00019-of-00031.safetensors",
+        "model.layers.49.mlp.down_proj.weight": "model-00019-of-00031.safetensors",
+        "model.layers.49.mlp.gate_proj.weight": "model-00019-of-00031.safetensors",
+        "model.layers.49.mlp.up_proj.weight": "model-00019-of-00031.safetensors",
+        "model.layers.49.post_attention_layernorm.weight": "model-00019-of-00031.safetensors",
+        "model.layers.49.self_attn.k_proj.bias": "model-00019-of-00031.safetensors",
+        "model.layers.49.self_attn.k_proj.weight": "model-00019-of-00031.safetensors",
+        "model.layers.49.self_attn.o_proj.weight": "model-00019-of-00031.safetensors",
+        "model.layers.49.self_attn.q_proj.bias": "model-00019-of-00031.safetensors",
+        "model.layers.49.self_attn.q_proj.weight": "model-00019-of-00031.safetensors",
+        "model.layers.49.self_attn.v_proj.bias": "model-00019-of-00031.safetensors",
+        "model.layers.49.self_attn.v_proj.weight": "model-00019-of-00031.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00003-of-00031.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00003-of-00031.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00031.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00003-of-00031.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00031.safetensors",
+        "model.layers.5.self_attn.k_proj.bias": "model-00003-of-00031.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00031.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00031.safetensors",
+        "model.layers.5.self_attn.q_proj.bias": "model-00003-of-00031.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00031.safetensors",
+        "model.layers.5.self_attn.v_proj.bias": "model-00003-of-00031.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00031.safetensors",
+        "model.layers.50.input_layernorm.weight": "model-00020-of-00031.safetensors",
+        "model.layers.50.mlp.down_proj.weight": "model-00020-of-00031.safetensors",
+        "model.layers.50.mlp.gate_proj.weight": "model-00019-of-00031.safetensors",
+        "model.layers.50.mlp.up_proj.weight": "model-00019-of-00031.safetensors",
+        "model.layers.50.post_attention_layernorm.weight": "model-00020-of-00031.safetensors",
+        "model.layers.50.self_attn.k_proj.bias": "model-00019-of-00031.safetensors",
+        "model.layers.50.self_attn.k_proj.weight": "model-00019-of-00031.safetensors",
+        "model.layers.50.self_attn.o_proj.weight": "model-00019-of-00031.safetensors",
+        "model.layers.50.self_attn.q_proj.bias": "model-00019-of-00031.safetensors",
+        "model.layers.50.self_attn.q_proj.weight": "model-00019-of-00031.safetensors",
+        "model.layers.50.self_attn.v_proj.bias": "model-00019-of-00031.safetensors",
+        "model.layers.50.self_attn.v_proj.weight": "model-00019-of-00031.safetensors",
+        "model.layers.51.input_layernorm.weight": "model-00020-of-00031.safetensors",
+        "model.layers.51.mlp.down_proj.weight": "model-00020-of-00031.safetensors",
+        "model.layers.51.mlp.gate_proj.weight": "model-00020-of-00031.safetensors",
+        "model.layers.51.mlp.up_proj.weight": "model-00020-of-00031.safetensors",
+        "model.layers.51.post_attention_layernorm.weight": "model-00020-of-00031.safetensors",
+        "model.layers.51.self_attn.k_proj.bias": "model-00020-of-00031.safetensors",
+        "model.layers.51.self_attn.k_proj.weight": "model-00020-of-00031.safetensors",
+        "model.layers.51.self_attn.o_proj.weight": "model-00020-of-00031.safetensors",
+        "model.layers.51.self_attn.q_proj.bias": "model-00020-of-00031.safetensors",
+        "model.layers.51.self_attn.q_proj.weight": "model-00020-of-00031.safetensors",
+        "model.layers.51.self_attn.v_proj.bias": "model-00020-of-00031.safetensors",
+        "model.layers.51.self_attn.v_proj.weight": "model-00020-of-00031.safetensors",
+        "model.layers.52.input_layernorm.weight": "model-00020-of-00031.safetensors",
+        "model.layers.52.mlp.down_proj.weight": "model-00020-of-00031.safetensors",
+        "model.layers.52.mlp.gate_proj.weight": "model-00020-of-00031.safetensors",
+        "model.layers.52.mlp.up_proj.weight": "model-00020-of-00031.safetensors",
+        "model.layers.52.post_attention_layernorm.weight": "model-00020-of-00031.safetensors",
+        "model.layers.52.self_attn.k_proj.bias": "model-00020-of-00031.safetensors",
+        "model.layers.52.self_attn.k_proj.weight": "model-00020-of-00031.safetensors",
+        "model.layers.52.self_attn.o_proj.weight": "model-00020-of-00031.safetensors",
+        "model.layers.52.self_attn.q_proj.bias": "model-00020-of-00031.safetensors",
+        "model.layers.52.self_attn.q_proj.weight": "model-00020-of-00031.safetensors",
+        "model.layers.52.self_attn.v_proj.bias": "model-00020-of-00031.safetensors",
+        "model.layers.52.self_attn.v_proj.weight": "model-00020-of-00031.safetensors",
+        "model.layers.53.input_layernorm.weight": "model-00021-of-00031.safetensors",
+        "model.layers.53.mlp.down_proj.weight": "model-00021-of-00031.safetensors",
+        "model.layers.53.mlp.gate_proj.weight": "model-00020-of-00031.safetensors",
+        "model.layers.53.mlp.up_proj.weight": "model-00021-of-00031.safetensors",
+        "model.layers.53.post_attention_layernorm.weight": "model-00021-of-00031.safetensors",
+        "model.layers.53.self_attn.k_proj.bias": "model-00020-of-00031.safetensors",
+        "model.layers.53.self_attn.k_proj.weight": "model-00020-of-00031.safetensors",
+        "model.layers.53.self_attn.o_proj.weight": "model-00020-of-00031.safetensors",
+        "model.layers.53.self_attn.q_proj.bias": "model-00020-of-00031.safetensors",
+        "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00031.safetensors",
+        "model.layers.53.self_attn.v_proj.bias": "model-00020-of-00031.safetensors",
+        "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00031.safetensors",
+        "model.layers.54.input_layernorm.weight": "model-00021-of-00031.safetensors",
+        "model.layers.54.mlp.down_proj.weight": "model-00021-of-00031.safetensors",
+        "model.layers.54.mlp.gate_proj.weight": "model-00021-of-00031.safetensors",
+        "model.layers.54.mlp.up_proj.weight": "model-00021-of-00031.safetensors",
+        "model.layers.54.post_attention_layernorm.weight": "model-00021-of-00031.safetensors",
+        "model.layers.54.self_attn.k_proj.bias": "model-00021-of-00031.safetensors",
+        "model.layers.54.self_attn.k_proj.weight": "model-00021-of-00031.safetensors",
+        "model.layers.54.self_attn.o_proj.weight": "model-00021-of-00031.safetensors",
+        "model.layers.54.self_attn.q_proj.bias": "model-00021-of-00031.safetensors",
+        "model.layers.54.self_attn.q_proj.weight": "model-00021-of-00031.safetensors",
+        "model.layers.54.self_attn.v_proj.bias": "model-00021-of-00031.safetensors",
+        "model.layers.54.self_attn.v_proj.weight": "model-00021-of-00031.safetensors",
+        "model.layers.55.input_layernorm.weight": "model-00021-of-00031.safetensors",
+        "model.layers.55.mlp.down_proj.weight": "model-00021-of-00031.safetensors",
+        "model.layers.55.mlp.gate_proj.weight": "model-00021-of-00031.safetensors",
+        "model.layers.55.mlp.up_proj.weight": "model-00021-of-00031.safetensors",
+        "model.layers.55.post_attention_layernorm.weight": "model-00021-of-00031.safetensors",
+        "model.layers.55.self_attn.k_proj.bias": "model-00021-of-00031.safetensors",
+        "model.layers.55.self_attn.k_proj.weight": "model-00021-of-00031.safetensors",
+        "model.layers.55.self_attn.o_proj.weight": "model-00021-of-00031.safetensors",
+        "model.layers.55.self_attn.q_proj.bias": "model-00021-of-00031.safetensors",
+        "model.layers.55.self_attn.q_proj.weight": "model-00021-of-00031.safetensors",
+        "model.layers.55.self_attn.v_proj.bias": "model-00021-of-00031.safetensors",
+        "model.layers.55.self_attn.v_proj.weight": "model-00021-of-00031.safetensors",
+        "model.layers.56.input_layernorm.weight": "model-00022-of-00031.safetensors",
+        "model.layers.56.mlp.down_proj.weight": "model-00022-of-00031.safetensors",
+        "model.layers.56.mlp.gate_proj.weight": "model-00022-of-00031.safetensors",
+        "model.layers.56.mlp.up_proj.weight": "model-00022-of-00031.safetensors",
+        "model.layers.56.post_attention_layernorm.weight": "model-00022-of-00031.safetensors",
+        "model.layers.56.self_attn.k_proj.bias": "model-00021-of-00031.safetensors",
+        "model.layers.56.self_attn.k_proj.weight": "model-00021-of-00031.safetensors",
+        "model.layers.56.self_attn.o_proj.weight": "model-00021-of-00031.safetensors",
+        "model.layers.56.self_attn.q_proj.bias": "model-00021-of-00031.safetensors",
+        "model.layers.56.self_attn.q_proj.weight": "model-00021-of-00031.safetensors",
+        "model.layers.56.self_attn.v_proj.bias": "model-00021-of-00031.safetensors",
+        "model.layers.56.self_attn.v_proj.weight": "model-00021-of-00031.safetensors",
+        "model.layers.57.input_layernorm.weight": "model-00022-of-00031.safetensors",
+        "model.layers.57.mlp.down_proj.weight": "model-00022-of-00031.safetensors",
+        "model.layers.57.mlp.gate_proj.weight": "model-00022-of-00031.safetensors",
+        "model.layers.57.mlp.up_proj.weight": "model-00022-of-00031.safetensors",
+        "model.layers.57.post_attention_layernorm.weight": "model-00022-of-00031.safetensors",
+        "model.layers.57.self_attn.k_proj.bias": "model-00022-of-00031.safetensors",
+        "model.layers.57.self_attn.k_proj.weight": "model-00022-of-00031.safetensors",
+        "model.layers.57.self_attn.o_proj.weight": "model-00022-of-00031.safetensors",
+        "model.layers.57.self_attn.q_proj.bias": "model-00022-of-00031.safetensors",
+        "model.layers.57.self_attn.q_proj.weight": "model-00022-of-00031.safetensors",
+        "model.layers.57.self_attn.v_proj.bias": "model-00022-of-00031.safetensors",
+        "model.layers.57.self_attn.v_proj.weight": "model-00022-of-00031.safetensors",
+        "model.layers.58.input_layernorm.weight": "model-00022-of-00031.safetensors",
+        "model.layers.58.mlp.down_proj.weight": "model-00022-of-00031.safetensors",
+        "model.layers.58.mlp.gate_proj.weight": "model-00022-of-00031.safetensors",
+        "model.layers.58.mlp.up_proj.weight": "model-00022-of-00031.safetensors",
+        "model.layers.58.post_attention_layernorm.weight": "model-00022-of-00031.safetensors",
+        "model.layers.58.self_attn.k_proj.bias": "model-00022-of-00031.safetensors",
+        "model.layers.58.self_attn.k_proj.weight": "model-00022-of-00031.safetensors",
+        "model.layers.58.self_attn.o_proj.weight": "model-00022-of-00031.safetensors",
+        "model.layers.58.self_attn.q_proj.bias": "model-00022-of-00031.safetensors",
+        "model.layers.58.self_attn.q_proj.weight": "model-00022-of-00031.safetensors",
+        "model.layers.58.self_attn.v_proj.bias": "model-00022-of-00031.safetensors",
+        "model.layers.58.self_attn.v_proj.weight": "model-00022-of-00031.safetensors",
+        "model.layers.59.input_layernorm.weight": "model-00023-of-00031.safetensors",
+        "model.layers.59.mlp.down_proj.weight": "model-00023-of-00031.safetensors",
+        "model.layers.59.mlp.gate_proj.weight": "model-00023-of-00031.safetensors",
+        "model.layers.59.mlp.up_proj.weight": "model-00023-of-00031.safetensors",
+        "model.layers.59.post_attention_layernorm.weight": "model-00023-of-00031.safetensors",
+        "model.layers.59.self_attn.k_proj.bias": "model-00023-of-00031.safetensors",
+        "model.layers.59.self_attn.k_proj.weight": "model-00023-of-00031.safetensors",
+        "model.layers.59.self_attn.o_proj.weight": "model-00023-of-00031.safetensors",
+        "model.layers.59.self_attn.q_proj.bias": "model-00023-of-00031.safetensors",
+        "model.layers.59.self_attn.q_proj.weight": "model-00023-of-00031.safetensors",
+        "model.layers.59.self_attn.v_proj.bias": "model-00023-of-00031.safetensors",
+        "model.layers.59.self_attn.v_proj.weight": "model-00023-of-00031.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00004-of-00031.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00004-of-00031.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00031.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00003-of-00031.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00031.safetensors",
+        "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00031.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00031.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00031.safetensors",
+        "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00031.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00031.safetensors",
+        "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00031.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00031.safetensors",
+        "model.layers.60.input_layernorm.weight": "model-00023-of-00031.safetensors",
+        "model.layers.60.mlp.down_proj.weight": "model-00023-of-00031.safetensors",
+        "model.layers.60.mlp.gate_proj.weight": "model-00023-of-00031.safetensors",
+        "model.layers.60.mlp.up_proj.weight": "model-00023-of-00031.safetensors",
+        "model.layers.60.post_attention_layernorm.weight": "model-00023-of-00031.safetensors",
+        "model.layers.60.self_attn.k_proj.bias": "model-00023-of-00031.safetensors",
+        "model.layers.60.self_attn.k_proj.weight": "model-00023-of-00031.safetensors",
+        "model.layers.60.self_attn.o_proj.weight": "model-00023-of-00031.safetensors",
+        "model.layers.60.self_attn.q_proj.bias": "model-00023-of-00031.safetensors",
+        "model.layers.60.self_attn.q_proj.weight": "model-00023-of-00031.safetensors",
+        "model.layers.60.self_attn.v_proj.bias": "model-00023-of-00031.safetensors",
+        "model.layers.60.self_attn.v_proj.weight": "model-00023-of-00031.safetensors",
+        "model.layers.61.input_layernorm.weight": "model-00024-of-00031.safetensors",
+        "model.layers.61.mlp.down_proj.weight": "model-00024-of-00031.safetensors",
+        "model.layers.61.mlp.gate_proj.weight": "model-00023-of-00031.safetensors",
+        "model.layers.61.mlp.up_proj.weight": "model-00023-of-00031.safetensors",
+        "model.layers.61.post_attention_layernorm.weight": "model-00024-of-00031.safetensors",
+        "model.layers.61.self_attn.k_proj.bias": "model-00023-of-00031.safetensors",
+        "model.layers.61.self_attn.k_proj.weight": "model-00023-of-00031.safetensors",
+        "model.layers.61.self_attn.o_proj.weight": "model-00023-of-00031.safetensors",
+        "model.layers.61.self_attn.q_proj.bias": "model-00023-of-00031.safetensors",
+        "model.layers.61.self_attn.q_proj.weight": "model-00023-of-00031.safetensors",
+        "model.layers.61.self_attn.v_proj.bias": "model-00023-of-00031.safetensors",
+        "model.layers.61.self_attn.v_proj.weight": "model-00023-of-00031.safetensors",
+        "model.layers.62.input_layernorm.weight": "model-00024-of-00031.safetensors",
+        "model.layers.62.mlp.down_proj.weight": "model-00024-of-00031.safetensors",
+        "model.layers.62.mlp.gate_proj.weight": "model-00024-of-00031.safetensors",
+        "model.layers.62.mlp.up_proj.weight": "model-00024-of-00031.safetensors",
+        "model.layers.62.post_attention_layernorm.weight": "model-00024-of-00031.safetensors",
+        "model.layers.62.self_attn.k_proj.bias": "model-00024-of-00031.safetensors",
+        "model.layers.62.self_attn.k_proj.weight": "model-00024-of-00031.safetensors",
+        "model.layers.62.self_attn.o_proj.weight": "model-00024-of-00031.safetensors",
+        "model.layers.62.self_attn.q_proj.bias": "model-00024-of-00031.safetensors",
+        "model.layers.62.self_attn.q_proj.weight": "model-00024-of-00031.safetensors",
+        "model.layers.62.self_attn.v_proj.bias": "model-00024-of-00031.safetensors",
+        "model.layers.62.self_attn.v_proj.weight": "model-00024-of-00031.safetensors",
+        "model.layers.63.input_layernorm.weight": "model-00024-of-00031.safetensors",
+        "model.layers.63.mlp.down_proj.weight": "model-00024-of-00031.safetensors",
+        "model.layers.63.mlp.gate_proj.weight": "model-00024-of-00031.safetensors",
+        "model.layers.63.mlp.up_proj.weight": "model-00024-of-00031.safetensors",
+        "model.layers.63.post_attention_layernorm.weight": "model-00024-of-00031.safetensors",
+        "model.layers.63.self_attn.k_proj.bias": "model-00024-of-00031.safetensors",
+        "model.layers.63.self_attn.k_proj.weight": "model-00024-of-00031.safetensors",
+        "model.layers.63.self_attn.o_proj.weight": "model-00024-of-00031.safetensors",
+        "model.layers.63.self_attn.q_proj.bias": "model-00024-of-00031.safetensors",
+        "model.layers.63.self_attn.q_proj.weight": "model-00024-of-00031.safetensors",
+        "model.layers.63.self_attn.v_proj.bias": "model-00024-of-00031.safetensors",
+        "model.layers.63.self_attn.v_proj.weight": "model-00024-of-00031.safetensors",
+        "model.layers.64.input_layernorm.weight": "model-00025-of-00031.safetensors",
+        "model.layers.64.mlp.down_proj.weight": "model-00025-of-00031.safetensors",
+        "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00031.safetensors",
+        "model.layers.64.mlp.up_proj.weight": "model-00025-of-00031.safetensors",
+        "model.layers.64.post_attention_layernorm.weight": "model-00025-of-00031.safetensors",
+        "model.layers.64.self_attn.k_proj.bias": "model-00024-of-00031.safetensors",
+        "model.layers.64.self_attn.k_proj.weight": "model-00024-of-00031.safetensors",
+        "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00031.safetensors",
+        "model.layers.64.self_attn.q_proj.bias": "model-00024-of-00031.safetensors",
+        "model.layers.64.self_attn.q_proj.weight": "model-00024-of-00031.safetensors",
+        "model.layers.64.self_attn.v_proj.bias": "model-00024-of-00031.safetensors",
+        "model.layers.64.self_attn.v_proj.weight": "model-00024-of-00031.safetensors",
+        "model.layers.65.input_layernorm.weight": "model-00025-of-00031.safetensors",
+        "model.layers.65.mlp.down_proj.weight": "model-00025-of-00031.safetensors",
+        "model.layers.65.mlp.gate_proj.weight": "model-00025-of-00031.safetensors",
+        "model.layers.65.mlp.up_proj.weight": "model-00025-of-00031.safetensors",
+        "model.layers.65.post_attention_layernorm.weight": "model-00025-of-00031.safetensors",
+        "model.layers.65.self_attn.k_proj.bias": "model-00025-of-00031.safetensors",
+        "model.layers.65.self_attn.k_proj.weight": "model-00025-of-00031.safetensors",
+        "model.layers.65.self_attn.o_proj.weight": "model-00025-of-00031.safetensors",
+        "model.layers.65.self_attn.q_proj.bias": "model-00025-of-00031.safetensors",
+        "model.layers.65.self_attn.q_proj.weight": "model-00025-of-00031.safetensors",
+        "model.layers.65.self_attn.v_proj.bias": "model-00025-of-00031.safetensors",
+        "model.layers.65.self_attn.v_proj.weight": "model-00025-of-00031.safetensors",
+        "model.layers.66.input_layernorm.weight": "model-00025-of-00031.safetensors",
+        "model.layers.66.mlp.down_proj.weight": "model-00025-of-00031.safetensors",
+        "model.layers.66.mlp.gate_proj.weight": "model-00025-of-00031.safetensors",
+        "model.layers.66.mlp.up_proj.weight": "model-00025-of-00031.safetensors",
+        "model.layers.66.post_attention_layernorm.weight": "model-00025-of-00031.safetensors",
+        "model.layers.66.self_attn.k_proj.bias": "model-00025-of-00031.safetensors",
+        "model.layers.66.self_attn.k_proj.weight": "model-00025-of-00031.safetensors",
+        "model.layers.66.self_attn.o_proj.weight": "model-00025-of-00031.safetensors",
+        "model.layers.66.self_attn.q_proj.bias": "model-00025-of-00031.safetensors",
+        "model.layers.66.self_attn.q_proj.weight": "model-00025-of-00031.safetensors",
+        "model.layers.66.self_attn.v_proj.bias": "model-00025-of-00031.safetensors",
+        "model.layers.66.self_attn.v_proj.weight": "model-00025-of-00031.safetensors",
+        "model.layers.67.input_layernorm.weight": "model-00026-of-00031.safetensors",
+        "model.layers.67.mlp.down_proj.weight": "model-00026-of-00031.safetensors",
+        "model.layers.67.mlp.gate_proj.weight": "model-00026-of-00031.safetensors",
+        "model.layers.67.mlp.up_proj.weight": "model-00026-of-00031.safetensors",
+        "model.layers.67.post_attention_layernorm.weight": "model-00026-of-00031.safetensors",
+        "model.layers.67.self_attn.k_proj.bias": "model-00025-of-00031.safetensors",
+        "model.layers.67.self_attn.k_proj.weight": "model-00025-of-00031.safetensors",
+        "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00031.safetensors",
+        "model.layers.67.self_attn.q_proj.bias": "model-00025-of-00031.safetensors",
+        "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00031.safetensors",
+        "model.layers.67.self_attn.v_proj.bias": "model-00025-of-00031.safetensors",
+        "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00031.safetensors",
+        "model.layers.68.input_layernorm.weight": "model-00026-of-00031.safetensors",
+        "model.layers.68.mlp.down_proj.weight": "model-00026-of-00031.safetensors",
+        "model.layers.68.mlp.gate_proj.weight": "model-00026-of-00031.safetensors",
+        "model.layers.68.mlp.up_proj.weight": "model-00026-of-00031.safetensors",
+        "model.layers.68.post_attention_layernorm.weight": "model-00026-of-00031.safetensors",
+        "model.layers.68.self_attn.k_proj.bias": "model-00026-of-00031.safetensors",
+        "model.layers.68.self_attn.k_proj.weight": "model-00026-of-00031.safetensors",
+        "model.layers.68.self_attn.o_proj.weight": "model-00026-of-00031.safetensors",
+        "model.layers.68.self_attn.q_proj.bias": "model-00026-of-00031.safetensors",
+        "model.layers.68.self_attn.q_proj.weight": "model-00026-of-00031.safetensors",
+        "model.layers.68.self_attn.v_proj.bias": "model-00026-of-00031.safetensors",
+        "model.layers.68.self_attn.v_proj.weight": "model-00026-of-00031.safetensors",
+        "model.layers.69.input_layernorm.weight": "model-00026-of-00031.safetensors",
+        "model.layers.69.mlp.down_proj.weight": "model-00026-of-00031.safetensors",
+        "model.layers.69.mlp.gate_proj.weight": "model-00026-of-00031.safetensors",
+        "model.layers.69.mlp.up_proj.weight": "model-00026-of-00031.safetensors",
+        "model.layers.69.post_attention_layernorm.weight": "model-00026-of-00031.safetensors",
+        "model.layers.69.self_attn.k_proj.bias": "model-00026-of-00031.safetensors",
+        "model.layers.69.self_attn.k_proj.weight": "model-00026-of-00031.safetensors",
+        "model.layers.69.self_attn.o_proj.weight": "model-00026-of-00031.safetensors",
+        "model.layers.69.self_attn.q_proj.bias": "model-00026-of-00031.safetensors",
+        "model.layers.69.self_attn.q_proj.weight": "model-00026-of-00031.safetensors",
+        "model.layers.69.self_attn.v_proj.bias": "model-00026-of-00031.safetensors",
+        "model.layers.69.self_attn.v_proj.weight": "model-00026-of-00031.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00004-of-00031.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00004-of-00031.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00031.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00004-of-00031.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00031.safetensors",
+        "model.layers.7.self_attn.k_proj.bias": "model-00004-of-00031.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00031.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00031.safetensors",
+        "model.layers.7.self_attn.q_proj.bias": "model-00004-of-00031.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00031.safetensors",
+        "model.layers.7.self_attn.v_proj.bias": "model-00004-of-00031.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00031.safetensors",
+        "model.layers.70.input_layernorm.weight": "model-00027-of-00031.safetensors",
+        "model.layers.70.mlp.down_proj.weight": "model-00027-of-00031.safetensors",
+        "model.layers.70.mlp.gate_proj.weight": "model-00027-of-00031.safetensors",
+        "model.layers.70.mlp.up_proj.weight": "model-00027-of-00031.safetensors",
+        "model.layers.70.post_attention_layernorm.weight": "model-00027-of-00031.safetensors",
+        "model.layers.70.self_attn.k_proj.bias": "model-00027-of-00031.safetensors",
+        "model.layers.70.self_attn.k_proj.weight": "model-00027-of-00031.safetensors",
+        "model.layers.70.self_attn.o_proj.weight": "model-00027-of-00031.safetensors",
+        "model.layers.70.self_attn.q_proj.bias": "model-00027-of-00031.safetensors",
+        "model.layers.70.self_attn.q_proj.weight": "model-00027-of-00031.safetensors",
+        "model.layers.70.self_attn.v_proj.bias": "model-00027-of-00031.safetensors",
+        "model.layers.70.self_attn.v_proj.weight": "model-00027-of-00031.safetensors",
+        "model.layers.71.input_layernorm.weight": "model-00027-of-00031.safetensors",
+        "model.layers.71.mlp.down_proj.weight": "model-00027-of-00031.safetensors",
+        "model.layers.71.mlp.gate_proj.weight": "model-00027-of-00031.safetensors",
+        "model.layers.71.mlp.up_proj.weight": "model-00027-of-00031.safetensors",
+        "model.layers.71.post_attention_layernorm.weight": "model-00027-of-00031.safetensors",
+        "model.layers.71.self_attn.k_proj.bias": "model-00027-of-00031.safetensors",
+        "model.layers.71.self_attn.k_proj.weight": "model-00027-of-00031.safetensors",
+        "model.layers.71.self_attn.o_proj.weight": "model-00027-of-00031.safetensors",
+        "model.layers.71.self_attn.q_proj.bias": "model-00027-of-00031.safetensors",
+        "model.layers.71.self_attn.q_proj.weight": "model-00027-of-00031.safetensors",
+        "model.layers.71.self_attn.v_proj.bias": "model-00027-of-00031.safetensors",
+        "model.layers.71.self_attn.v_proj.weight": "model-00027-of-00031.safetensors",
+        "model.layers.72.input_layernorm.weight": "model-00028-of-00031.safetensors",
+        "model.layers.72.mlp.down_proj.weight": "model-00028-of-00031.safetensors",
+        "model.layers.72.mlp.gate_proj.weight": "model-00027-of-00031.safetensors",
+        "model.layers.72.mlp.up_proj.weight": "model-00027-of-00031.safetensors",
+        "model.layers.72.post_attention_layernorm.weight": "model-00028-of-00031.safetensors",
+        "model.layers.72.self_attn.k_proj.bias": "model-00027-of-00031.safetensors",
+        "model.layers.72.self_attn.k_proj.weight": "model-00027-of-00031.safetensors",
+        "model.layers.72.self_attn.o_proj.weight": "model-00027-of-00031.safetensors",
+        "model.layers.72.self_attn.q_proj.bias": "model-00027-of-00031.safetensors",
+        "model.layers.72.self_attn.q_proj.weight": "model-00027-of-00031.safetensors",
+        "model.layers.72.self_attn.v_proj.bias": "model-00027-of-00031.safetensors",
+        "model.layers.72.self_attn.v_proj.weight": "model-00027-of-00031.safetensors",
+        "model.layers.73.input_layernorm.weight": "model-00028-of-00031.safetensors",
+        "model.layers.73.mlp.down_proj.weight": "model-00028-of-00031.safetensors",
+        "model.layers.73.mlp.gate_proj.weight": "model-00028-of-00031.safetensors",
+        "model.layers.73.mlp.up_proj.weight": "model-00028-of-00031.safetensors",
+        "model.layers.73.post_attention_layernorm.weight": "model-00028-of-00031.safetensors",
+        "model.layers.73.self_attn.k_proj.bias": "model-00028-of-00031.safetensors",
+        "model.layers.73.self_attn.k_proj.weight": "model-00028-of-00031.safetensors",
+        "model.layers.73.self_attn.o_proj.weight": "model-00028-of-00031.safetensors",
+        "model.layers.73.self_attn.q_proj.bias": "model-00028-of-00031.safetensors",
+        "model.layers.73.self_attn.q_proj.weight": "model-00028-of-00031.safetensors",
+        "model.layers.73.self_attn.v_proj.bias": "model-00028-of-00031.safetensors",
+        "model.layers.73.self_attn.v_proj.weight": "model-00028-of-00031.safetensors",
+        "model.layers.74.input_layernorm.weight": "model-00028-of-00031.safetensors",
+        "model.layers.74.mlp.down_proj.weight": "model-00028-of-00031.safetensors",
+        "model.layers.74.mlp.gate_proj.weight": "model-00028-of-00031.safetensors",
+        "model.layers.74.mlp.up_proj.weight": "model-00028-of-00031.safetensors",
+        "model.layers.74.post_attention_layernorm.weight": "model-00028-of-00031.safetensors",
+        "model.layers.74.self_attn.k_proj.bias": "model-00028-of-00031.safetensors",
+        "model.layers.74.self_attn.k_proj.weight": "model-00028-of-00031.safetensors",
+        "model.layers.74.self_attn.o_proj.weight": "model-00028-of-00031.safetensors",
+        "model.layers.74.self_attn.q_proj.bias": "model-00028-of-00031.safetensors",
+        "model.layers.74.self_attn.q_proj.weight": "model-00028-of-00031.safetensors",
+        "model.layers.74.self_attn.v_proj.bias": "model-00028-of-00031.safetensors",
+        "model.layers.74.self_attn.v_proj.weight": "model-00028-of-00031.safetensors",
+        "model.layers.75.input_layernorm.weight": "model-00029-of-00031.safetensors",
+        "model.layers.75.mlp.down_proj.weight": "model-00029-of-00031.safetensors",
+        "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00031.safetensors",
+        "model.layers.75.mlp.up_proj.weight": "model-00029-of-00031.safetensors",
+        "model.layers.75.post_attention_layernorm.weight": "model-00029-of-00031.safetensors",
+        "model.layers.75.self_attn.k_proj.bias": "model-00028-of-00031.safetensors",
+        "model.layers.75.self_attn.k_proj.weight": "model-00028-of-00031.safetensors",
+        "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00031.safetensors",
+        "model.layers.75.self_attn.q_proj.bias": "model-00028-of-00031.safetensors",
+        "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00031.safetensors",
+        "model.layers.75.self_attn.v_proj.bias": "model-00028-of-00031.safetensors",
+        "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00031.safetensors",
+        "model.layers.76.input_layernorm.weight": "model-00029-of-00031.safetensors",
+        "model.layers.76.mlp.down_proj.weight": "model-00029-of-00031.safetensors",
+        "model.layers.76.mlp.gate_proj.weight": "model-00029-of-00031.safetensors",
+        "model.layers.76.mlp.up_proj.weight": "model-00029-of-00031.safetensors",
+        "model.layers.76.post_attention_layernorm.weight": "model-00029-of-00031.safetensors",
+        "model.layers.76.self_attn.k_proj.bias": "model-00029-of-00031.safetensors",
+        "model.layers.76.self_attn.k_proj.weight": "model-00029-of-00031.safetensors",
+        "model.layers.76.self_attn.o_proj.weight": "model-00029-of-00031.safetensors",
+        "model.layers.76.self_attn.q_proj.bias": "model-00029-of-00031.safetensors",
+        "model.layers.76.self_attn.q_proj.weight": "model-00029-of-00031.safetensors",
+        "model.layers.76.self_attn.v_proj.bias": "model-00029-of-00031.safetensors",
+        "model.layers.76.self_attn.v_proj.weight": "model-00029-of-00031.safetensors",
+        "model.layers.77.input_layernorm.weight": "model-00029-of-00031.safetensors",
+        "model.layers.77.mlp.down_proj.weight": "model-00029-of-00031.safetensors",
+        "model.layers.77.mlp.gate_proj.weight": "model-00029-of-00031.safetensors",
+        "model.layers.77.mlp.up_proj.weight": "model-00029-of-00031.safetensors",
+        "model.layers.77.post_attention_layernorm.weight": "model-00029-of-00031.safetensors",
+        "model.layers.77.self_attn.k_proj.bias": "model-00029-of-00031.safetensors",
+        "model.layers.77.self_attn.k_proj.weight": "model-00029-of-00031.safetensors",
+        "model.layers.77.self_attn.o_proj.weight": "model-00029-of-00031.safetensors",
+        "model.layers.77.self_attn.q_proj.bias": "model-00029-of-00031.safetensors",
+        "model.layers.77.self_attn.q_proj.weight": "model-00029-of-00031.safetensors",
+        "model.layers.77.self_attn.v_proj.bias": "model-00029-of-00031.safetensors",
+        "model.layers.77.self_attn.v_proj.weight": "model-00029-of-00031.safetensors",
+        "model.layers.78.input_layernorm.weight": "model-00030-of-00031.safetensors",
+        "model.layers.78.mlp.down_proj.weight": "model-00030-of-00031.safetensors",
+        "model.layers.78.mlp.gate_proj.weight": "model-00030-of-00031.safetensors",
+        "model.layers.78.mlp.up_proj.weight": "model-00030-of-00031.safetensors",
+        "model.layers.78.post_attention_layernorm.weight": "model-00030-of-00031.safetensors",
+        "model.layers.78.self_attn.k_proj.bias": "model-00029-of-00031.safetensors",
+        "model.layers.78.self_attn.k_proj.weight": "model-00029-of-00031.safetensors",
+        "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00031.safetensors",
+        "model.layers.78.self_attn.q_proj.bias": "model-00029-of-00031.safetensors",
+        "model.layers.78.self_attn.q_proj.weight": "model-00029-of-00031.safetensors",
+        "model.layers.78.self_attn.v_proj.bias": "model-00029-of-00031.safetensors",
+        "model.layers.78.self_attn.v_proj.weight": "model-00029-of-00031.safetensors",
+        "model.layers.79.input_layernorm.weight": "model-00030-of-00031.safetensors",
+        "model.layers.79.mlp.down_proj.weight": "model-00030-of-00031.safetensors",
+        "model.layers.79.mlp.gate_proj.weight": "model-00030-of-00031.safetensors",
+        "model.layers.79.mlp.up_proj.weight": "model-00030-of-00031.safetensors",
+        "model.layers.79.post_attention_layernorm.weight": "model-00030-of-00031.safetensors",
+        "model.layers.79.self_attn.k_proj.bias": "model-00030-of-00031.safetensors",
+        "model.layers.79.self_attn.k_proj.weight": "model-00030-of-00031.safetensors",
+        "model.layers.79.self_attn.o_proj.weight": "model-00030-of-00031.safetensors",
+        "model.layers.79.self_attn.q_proj.bias": "model-00030-of-00031.safetensors",
+        "model.layers.79.self_attn.q_proj.weight": "model-00030-of-00031.safetensors",
+        "model.layers.79.self_attn.v_proj.bias": "model-00030-of-00031.safetensors",
+        "model.layers.79.self_attn.v_proj.weight": "model-00030-of-00031.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00004-of-00031.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00004-of-00031.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00031.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00004-of-00031.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00031.safetensors",
+        "model.layers.8.self_attn.k_proj.bias": "model-00004-of-00031.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00031.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00031.safetensors",
+        "model.layers.8.self_attn.q_proj.bias": "model-00004-of-00031.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00031.safetensors",
+        "model.layers.8.self_attn.v_proj.bias": "model-00004-of-00031.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00031.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00005-of-00031.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00005-of-00031.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00031.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00005-of-00031.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00031.safetensors",
+        "model.layers.9.self_attn.k_proj.bias": "model-00004-of-00031.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00031.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00031.safetensors",
+        "model.layers.9.self_attn.q_proj.bias": "model-00004-of-00031.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00031.safetensors",
+        "model.layers.9.self_attn.v_proj.bias": "model-00004-of-00031.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00031.safetensors",
+        "model.norm.weight": "model-00030-of-00031.safetensors"
+    }
+}