Upload LlamaForCausalLM (#1)

- Upload LlamaForCausalLM (d0d17210a2037e645789f0bedf0b4b3e8fde0f44)

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "01-ai/Yi-34B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 56,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 5000000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 64000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.2"
+}

model-00001-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de440ae849dc5062e8a0a81f4d81d7a7fe9eddf9dccebc98dd27f162b4854704
+size 1739588416

model-00002-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28cf4b572458ca4369c66d825e5ae116b84cf5975fea19243108b7f01541df24
+size 1937827776

model-00003-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00f53d312a855f7e4411335d482a670b6518a02ca5c7fba7322a095541311e03
+size 1937827776

model-00004-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97a990bc1495de1f568a69d952e2b5b84da3884d85086d72a03cfd577ff3a2f2
+size 1996547680

model-00005-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f56be660675281c1b7b0d7617df47d4dd38f073e378a517e833e7680af7db70
+size 1937798872

model-00006-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a74a55da74b69433d1a0498fc73360c997860cb578f38c5916368f1868605729
+size 1937827776

model-00007-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c191e3bcdda7dae41899034ad5f584c03a6fbe774e31060a62f2ed5385ab250
+size 1937827784

model-00008-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8e0c5362168f9eccbbe39756cf46d124b823a85ad5b3ffd0dd231beb447c1df
+size 1996547696

model-00009-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aee0d93266f87679a27ac670ce44ba08a49a0bd7bacc15c1fff00da7255c4765
+size 1937798888

model-00010-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5078cfa92d8c0cb3caa3080ecdd0a51b9a9ce0c14111935e835405893286441
+size 1937827792

model-00011-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd6e3f0848d7ec7e8ad5209f8b7babf0f45860d1238014c53dd362b9b25276ac
+size 1937827792

model-00012-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:682e0a979854c840ee2a0c7d840b4b795d06ddf8355e8a20bf30d178641af1dd
+size 1996547696

model-00013-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22e6ac33a4670967b44db11bc235341750f2d054abde3d0bef6e17355f8832ba
+size 1937798888

model-00014-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1636238c6ae4f1f31f68e66adb2ac523f159949e0c819bec381244bf7ed14f89
+size 1937827792

model-00015-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f94c072494566ccb40a720495daf41531a00a737f0bb584a4af6ddb99aede72b
+size 1937827792

model-00016-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf3b01631462c5b44913c2f52495f100960c8801ac6e5f44ecf8ebfaab575de2
+size 1996547696

model-00017-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f124e715960835e5daaaf60fc9cde5f34338349603edce18bb170da57951451
+size 1937798888

model-00018-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0473e769030dc76d9fffefa750717ea4ca48463e18380977b135451cfb6ee01e
+size 1937827792

model-00019-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29f1da9438fefcfa9e8583240f985b6c330312553fca38278fcfcecb9c19f9f6
+size 1937827792

model-00020-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f70d73b0208a8a58fae0e160d48e59b919d86bd76cb6b6661eb9bceb5ba2c1a2
+size 1996547696

model-00021-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fca659c8f5a42319385ca7fc48e5f77e4f213b921abe4ce365e7c2df53061f4
+size 1937798888

model-00022-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ddc0be0570ee5c556b66170819467e940e48894f7032637281a553e2a0baff0
+size 1937827792

model-00023-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:727814656586bfc25216be74c9514e9f143300295c30b15bd0fe051cc144b2ea
+size 1937827792

model-00024-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e23ce4a1c2c167de3750770adf85b7cc586a16c30e5de3661956daf33d264bc3
+size 1996547696

model-00025-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce4bc45c66658a3cce1d3fe3eb8a79aa5bc653c070e1b6176542c44dbdb3b4c8
+size 1937798888

model-00026-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fee9de52c1cbb1c345d2d1f1b84109402b2605d050707dcc2d58ce886daec7a
+size 1937827792

model-00027-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d99f93b764953b820f5327065d41f63e6dc0581f618751ae0acb81f0517b76d
+size 1937827792

model-00028-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:027613a5c63dc62ccc828d8295965f5d5ca0f986dd6409ab5e6c32ae5336079d
+size 1996547696

model-00029-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65430c7a6fbd0b8afe2ad7bb232ebe47b1c10e1ce94b62fe6adb99a8368996ae
+size 1937798888

model-00030-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef1abca524842909f72b576a69c3fac22f144b55e9573b47de86921c73a25f29
+size 1937827792

model-00031-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b52647341dfb343846d60df50152cf378a3d928d9deec40640b49a28b0de1e3
+size 1937827792

model-00032-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:916f1502f453872b9df107c13f6eaff2bab69d8c3c989670845c2ac982a4331d
+size 1996547696

model-00033-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36f5dce3a432c16bc2af8ebf0e084857c6f562a8b8e32f05cc01ded5716f86e5
+size 1937798888

model-00034-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:056c0ec00bd1abf52be4fdb8b990af6834ecc7e762cb730a8281214afbefeaca
+size 1937827792

model-00035-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffd0aa04060944bf32a3ea4db05cbf231ce60c49f6f529deb5676bf2b8a7776f
+size 1702960720

model-00036-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18622e7b74d4645c26e592e75c7d3d2b83d875eaae1e8965d76f7f3de933528f
+size 917504128

model.safetensors.index.json

@@ -0,0 +1,550 @@
+{
+  "metadata": {
+    "total_size": 68777834496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00036-of-00036.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00036.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00036.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00036.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00036.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00036.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00036.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00036.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00036.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00036.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00036.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00036.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00007-of-00036.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00036.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00008-of-00036.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00008-of-00036.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00008-of-00036.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00008-of-00036.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00009-of-00036.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00009-of-00036.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00010-of-00036.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00010-of-00036.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00010-of-00036.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00036.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00011-of-00036.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00036.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00011-of-00036.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00011-of-00036.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00012-of-00036.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00012-of-00036.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00012-of-00036.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00012-of-00036.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00003-of-00036.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00036.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00013-of-00036.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00036.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00014-of-00036.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00014-of-00036.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00014-of-00036.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00036.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00015-of-00036.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00036.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00015-of-00036.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00015-of-00036.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00016-of-00036.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00016-of-00036.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00016-of-00036.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00016-of-00036.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00017-of-00036.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00017-of-00036.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00018-of-00036.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00018-of-00036.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00018-of-00036.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00018-of-00036.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00036.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00036.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00019-of-00036.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00019-of-00036.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00019-of-00036.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00019-of-00036.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00020-of-00036.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00020-of-00036.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00020-of-00036.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00020-of-00036.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00021-of-00036.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00021-of-00036.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00022-of-00036.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00022-of-00036.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00022-of-00036.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00022-of-00036.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00023-of-00036.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00023-of-00036.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00023-of-00036.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00023-of-00036.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00024-of-00036.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00024-of-00036.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00004-of-00036.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00036.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00024-of-00036.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00024-of-00036.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00025-of-00036.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00025-of-00036.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00026-of-00036.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00026-of-00036.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00026-of-00036.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00026-of-00036.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00027-of-00036.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00027-of-00036.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00027-of-00036.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00027-of-00036.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00028-of-00036.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00028-of-00036.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00028-of-00036.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00028-of-00036.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00029-of-00036.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00029-of-00036.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00030-of-00036.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00030-of-00036.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00004-of-00036.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00036.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00030-of-00036.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00030-of-00036.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00031-of-00036.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00031-of-00036.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00031-of-00036.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00031-of-00036.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00032-of-00036.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00032-of-00036.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00032-of-00036.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00032-of-00036.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00033-of-00036.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00033-of-00036.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00034-of-00036.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00034-of-00036.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00034-of-00036.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00034-of-00036.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00035-of-00036.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00035-of-00036.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00035-of-00036.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00035-of-00036.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00005-of-00036.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00036.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00006-of-00036.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00036.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00006-of-00036.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00036.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00007-of-00036.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00007-of-00036.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00036.safetensors",
+    "model.norm.weight": "model-00035-of-00036.safetensors"
+  }
+}