Upload LlamaForCausalLM (#1)

- Upload LlamaForCausalLM (15f4dbaa1424d3e7ac7d20f492f17fc94ed35b7f)

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "chargoddard/Yi-34B-Llama",
+  "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": "4.39.2",
+  "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": "4.39.2"
+}

model-00001-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51ec479b7b99ed43a9059c0ed55497f30c3d5a5bbe7562b623502336b71f2e08
+size 1739588416

model-00002-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0039cd0b420e31f9dbb27090da804594f1317f6bdced8306edec64d3fb915306
+size 1937827776

model-00003-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0c243f24aa7ec02eb2cbccaedaf9c838605abd08602abd1d064c62163c2df27
+size 1937827776

model-00004-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec1b055523d5cb07d64cfa5099adca9d5808f2ed571653f8d2adbf2a8f0124a6
+size 1996547680

model-00005-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4c03d48e2b375c66a6cf4163d80fadfd2a441c19d42c50f0b0331b4ff46cbbe
+size 1937798872

model-00006-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a50f96a206f7f469bb198b1fc9a3a8a95af5dada1aa31cf73ab5c3aa959e0b12
+size 1937827776

model-00007-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:891a75937bac2628bcdb83f31302d62a7d8555ab529dff7184068ada2a86611e
+size 1937827784

model-00008-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e210cc57f578098fe7602a5acc58378eb84df33e428cdc7e31a94eb2aae4cb10
+size 1996547696

model-00009-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4087ac3303c22cac4b6e43804f9f74474a7b81dc444e002f4b594f08df3d7057
+size 1937798888

model-00010-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cbe5f2dae9bde86f84887ffcfe786294636299570ecc5909a084cca85c8a3aa
+size 1937827792

model-00011-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36f78ff54a8f00c87132132a43e645fbadc1f158c4839f16eb610be540cd6eb0
+size 1937827792

model-00012-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90075124ca55a95927186db07b1b17e92b450f8e150869f9b6c535bcf949ae70
+size 1996547696

model-00013-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c70cc774bc9bc1f9d1d6b3680429a48aba297eeef30bb97df15268a8deb750c9
+size 1937798888

model-00014-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38a62b3f60c57439f8976287e07aee649e7820226a4b4fe0b218f35c0b53a556
+size 1937827792

model-00015-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee435caf4c6044a04c7dd6ee271ecbde549e4398ab685a4a87fcb78d557de12d
+size 1937827792

model-00016-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de21dc7da44ed35bd5cfd490210eb95e5ccfa903957de55331c71900052476f2
+size 1996547696

model-00017-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab2c2854139c9b03c6c0837538dfe5eed9f732733cf1139fb1f2ecd9e6ff2763
+size 1937798888

model-00018-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce148934c4a87192bc0815bbf365c57657d210d9ffe2181d49b2187353204605
+size 1937827792

model-00019-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0740fbf7eb0b10c11d0e5e9bbdae0314720635f63adefc09537144d6a46d09f
+size 1937827792

model-00020-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5a1a50747007eca38bf3c168960e9120a2505abe9285f58676478c39d71edbe
+size 1996547696

model-00021-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:674c16e9244233e5964e2211dc95743c1445ddac9bfbe10c8934932643792647
+size 1937798888

model-00022-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc4bc4bf0c0db87df9aca8a76a48f21c165070f0f88b6bb331a9accc16452f01
+size 1937827792

model-00023-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82565ee9e1c74af67fa8264bbb8f6dd0f43a7f9fa7d738911d375b849186a0f7
+size 1937827792

model-00024-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4e9c0337f032cf4be4eef1f4ff0fbbced428090e866b69438f82abaecbb2c92
+size 1996547696

model-00025-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff1c1c7095f5ac5611e2189b7e51516d4dec1d8bb4572ce5c0ce4b5233d0f185
+size 1937798888

model-00026-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fba22d1ca35da737f7b18b6eb029a13663689c892e993a8f3989475b483c86a
+size 1937827792

model-00027-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29410ff24e074e6ddbf7206cc9640857e425ba3857254f4ccd240a65ef222fe2
+size 1937827792

model-00028-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cae91816fef610db5a97a3b307502788d6f5f74404a5ae04bccef5c66ce839b6
+size 1996547696

model-00029-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e911df9575639faa26218a8aeb69506ef6462fce787715a7e85c5c83702db670
+size 1937798888

model-00030-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39bf83e2f0a95c9e25bfef158d892ca75dc523a04faee2ea84144f540ca7af77
+size 1937827792

model-00031-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf9a2f2e6fbc06f36cd669c38d15c482f5059fcd5dc74e655e3d12cea50dfae2
+size 1937827792

model-00032-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77cd00de03c7988d7e4a99214d3b05e857c1492a3a43d2236891eebcc978a1de
+size 1996547696

model-00033-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bba30306b864aa9edf026d3e78d9676ed3b5d093838893c67195deb595d27aac
+size 1937798888

model-00034-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:327973b15802816681d3c76a0e08d0fea516e7f319fb5e04991c7d7625c71c30
+size 1937827792

model-00035-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aab269b9f3008b7b7e6e92be696060640607ca12801c857d26a5cb3d1911e58
+size 1702960720

model-00036-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06c3aa616917635a54c9d0e0eea8a86e8b69a32ffcec95d84a58d3da67456ca2
+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"
+  }
+}