CoLeG-Math-70B

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/project/ugmathllm/xxuca/checkpoints/Llama-2-70b-chat-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.0",
+  "use_cache": false,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.39.0"
+}

model-00001-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2bd72c7b486438d0c3b502a50493d10dd90d50f5d211c54366c937e37088129
+size 4718676720

model-00002-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2369e31bab4138a6c194bae2566bbcde3564beb50b6f8fd0e10bd58f44ac284
+size 4664167376

model-00003-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28d95d5c528b6f8ac147ad704f49b87bb45ba990429abd867224d0d9e85bd7be
+size 4999711704

model-00004-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bd7e34cdcd1c56b07320330fc7ba403df424540e1caa08a3d27e0b1b4f626a9
+size 4966157048

model-00005-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf7bfde22bac84aaee3bad3614e9e2c2622ac86a22518f1517b50111cd01d8ef
+size 4664134408

model-00006-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2329dbd1d28f28a2708384fb92c2a79a1cf995a1f7d14cf24b2b5cf2ba5cbd91
+size 4664167408

model-00007-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aafa8ce29e845143e1e4e5b0478e409d60f8720c19de134e2f7cad08fea8032
+size 4664167408

model-00008-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31f5899968d131e284380f9a617a20fbb172a0e0e175c306481b56370c71e849
+size 4999711728

model-00009-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b9e63f9a37e5907636bc66eaf8961a23dde9d6669e7dda894f4c51c4f6b0656
+size 4966157056

model-00010-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c1f4007549f5da847726d2f752481c50f7a6c4a12fb76d421adb16e3cdae151
+size 4664134408

model-00011-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9043a0e138991d9b1f5eee3dab593f4a7bd33f2824b83a0547458621175fb326
+size 4664167408

model-00012-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0cab2abd616f8a489b965604edbf06a4ec7395983f81b79db0d87ea71d556da
+size 4664167408

model-00013-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c44ca4598e4329c6390b6da77edd7b510f905cab9e5849b642eaf0ddc103ec62
+size 4999711728

model-00014-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf56ac06ec4d19eb4852fa47ef4ef0bbd5271bb3d102fbf2dde7b3a7b44f698d
+size 4966157056

model-00015-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fcdf57ecd682ac01dd2ec0bf414c2369bfb3431ad3397a8ffaffba876736ea9
+size 4664134408

model-00016-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6250a94ec1ccae9a8b4915b0be9ae7437dc57c7814d29aab5acdbe82ac323c41
+size 4664167408

model-00017-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17a15b51aebfc2ba2d72e01ffecdc36114512afd4b04b3d4817375892cefc46f
+size 4664167408

model-00018-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9ae4b4f162a3495321c434b29d96cace8958df3fc560774a4edea0642b85ffa
+size 4999711728

model-00019-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18bc7d99400bedf658a33a08737c3e2701eed3d0431002feea634e324bd95282
+size 4966157056

model-00020-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f7d2405f2f7c31693ca620eff20a3ea36eeef83e79346471c2aaaf05f801d8e
+size 4664134408

model-00021-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f74e736470aa86281e8ec2274c004051e4a514e6aab3766d433e1bb77fcf338
+size 4664167408

model-00022-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0726482b80fcc874b659df59423de6ebef3883c68337cfa27196ba0f7d8032bd
+size 4664167408

model-00023-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfe71d494485e162fb40a897e22c4ae984bf1e69d8a0908683ce5ed890ae9cd5
+size 4999711728

model-00024-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b0c2812287be355cceace7906747aab562870396447a7912855bcf63967fcb7
+size 4966157056

model-00025-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15c31380e0befbeb84357edc1d3c57acf32e33ec3d2ae8be412c330c009dc0fb
+size 4664134408

model-00026-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a644b1f0de1bb793862d8ea1eb683afbf18cbc48d01cb6bd77230f4d8587a49f
+size 4664167408

model-00027-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a308b8d21e79d4b47cb5f15c23654efc18279dd6c00ce2be7d9a011710e8db4
+size 4664167408

model-00028-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17a62c7aa1d81b9d53c1e19823f8355055fd876b507c6e750668fe4086e28762
+size 4999711728

model-00029-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f58d72d112629c681f4dfc45bf176530a4947f1ee6d89aee155a6c50ab140b5f
+size 3779168168

model.safetensors.index.json

@@ -0,0 +1,730 @@
+{
+  "metadata": {
+    "total_size": 137953329152
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00029-of-00029.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.64.input_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.64.mlp.down_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.64.mlp.up_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.64.post_attention_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.64.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.64.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.64.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.65.input_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.mlp.down_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.mlp.up_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.post_attention_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.self_attn.k_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.self_attn.o_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.self_attn.q_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.self_attn.v_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.input_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.mlp.down_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.mlp.up_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.post_attention_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.self_attn.k_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.self_attn.o_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.self_attn.q_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.self_attn.v_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.67.input_layernorm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.mlp.down_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.mlp.gate_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.post_attention_layernorm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.self_attn.k_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.input_layernorm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.mlp.down_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.mlp.gate_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.post_attention_layernorm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.self_attn.k_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.self_attn.o_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.self_attn.q_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.self_attn.v_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.69.input_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.69.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.69.mlp.gate_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.69.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.69.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.69.self_attn.k_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.69.self_attn.o_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.69.self_attn.q_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.69.self_attn.v_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.70.input_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.mlp.gate_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.mlp.up_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.input_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.mlp.gate_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.mlp.up_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.72.input_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.72.mlp.down_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.72.mlp.gate_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.72.mlp.up_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.72.post_attention_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.72.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.72.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.72.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.72.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.73.input_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.mlp.down_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.mlp.up_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.post_attention_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.self_attn.k_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.self_attn.o_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.self_attn.q_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.self_attn.v_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.input_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.mlp.down_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.mlp.gate_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.mlp.up_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.post_attention_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.self_attn.k_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.self_attn.o_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.self_attn.q_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.self_attn.v_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.75.input_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.75.mlp.down_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.75.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.75.self_attn.k_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.75.self_attn.o_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.75.self_attn.q_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.75.self_attn.v_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.76.input_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.mlp.down_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.mlp.gate_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.post_attention_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.self_attn.k_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.self_attn.o_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.self_attn.q_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.self_attn.v_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.input_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.mlp.down_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.mlp.gate_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.post_attention_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.self_attn.k_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.self_attn.o_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.self_attn.q_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.self_attn.v_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.78.input_layernorm.weight": "model-00029-of-00029.safetensors",
+    "model.layers.78.mlp.down_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.78.mlp.gate_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.78.mlp.up_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.78.post_attention_layernorm.weight": "model-00029-of-00029.safetensors",
+    "model.layers.78.self_attn.k_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.78.self_attn.q_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.78.self_attn.v_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.79.input_layernorm.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.mlp.down_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.mlp.gate_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.mlp.up_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.post_attention_layernorm.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.self_attn.k_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.self_attn.o_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.self_attn.q_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.self_attn.v_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00029.safetensors",
+    "model.norm.weight": "model-00029-of-00029.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,345 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.625,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 0.4546,
+      "step": 20
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.41796875,
+      "learning_rate": 9.994529604032901e-06,
+      "loss": 0.2781,
+      "step": 40
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.38671875,
+      "learning_rate": 9.964784918620284e-06,
+      "loss": 0.2492,
+      "step": 60
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.3984375,
+      "learning_rate": 9.909333658705933e-06,
+      "loss": 0.2379,
+      "step": 80
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.400390625,
+      "learning_rate": 9.82846293883108e-06,
+      "loss": 0.2301,
+      "step": 100
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.37109375,
+      "learning_rate": 9.722591489961829e-06,
+      "loss": 0.2255,
+      "step": 120
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.388671875,
+      "learning_rate": 9.59226749139145e-06,
+      "loss": 0.2223,
+      "step": 140
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.76171875,
+      "learning_rate": 9.438165732387471e-06,
+      "loss": 0.2171,
+      "step": 160
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.39453125,
+      "learning_rate": 9.261084118279846e-06,
+      "loss": 0.2154,
+      "step": 180
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.41015625,
+      "learning_rate": 9.06193953908105e-06,
+      "loss": 0.2126,
+      "step": 200
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.37109375,
+      "learning_rate": 8.84176312202936e-06,
+      "loss": 0.2143,
+      "step": 220
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.37890625,
+      "learning_rate": 8.601694892636701e-06,
+      "loss": 0.2082,
+      "step": 240
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.369140625,
+      "learning_rate": 8.34297787188496e-06,
+      "loss": 0.2072,
+      "step": 260
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.404296875,
+      "learning_rate": 8.066951640134183e-06,
+      "loss": 0.2069,
+      "step": 280
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.404296875,
+      "learning_rate": 7.77504540106735e-06,
+      "loss": 0.2067,
+      "step": 300
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.431640625,
+      "learning_rate": 7.468770581585147e-06,
+      "loss": 0.1909,
+      "step": 320
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.39453125,
+      "learning_rate": 7.149713005966784e-06,
+      "loss": 0.1909,
+      "step": 340
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.400390625,
+      "learning_rate": 6.819524684817439e-06,
+      "loss": 0.1877,
+      "step": 360
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 0.396484375,
+      "learning_rate": 6.479915261317299e-06,
+      "loss": 0.1901,
+      "step": 380
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 0.404296875,
+      "learning_rate": 6.132643159061707e-06,
+      "loss": 0.1886,
+      "step": 400
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.376953125,
+      "learning_rate": 5.779506477326933e-06,
+      "loss": 0.1887,
+      "step": 420
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 0.404296875,
+      "learning_rate": 5.4223336809039205e-06,
+      "loss": 0.1866,
+      "step": 440
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 0.419921875,
+      "learning_rate": 5.062974132706017e-06,
+      "loss": 0.1887,
+      "step": 460
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.390625,
+      "learning_rate": 4.703288518170774e-06,
+      "loss": 0.1849,
+      "step": 480
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 0.390625,
+      "learning_rate": 4.345139211036192e-06,
+      "loss": 0.187,
+      "step": 500
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 0.421875,
+      "learning_rate": 3.9903806303753036e-06,
+      "loss": 0.1839,
+      "step": 520
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.40234375,
+      "learning_rate": 3.6408496388182857e-06,
+      "loss": 0.187,
+      "step": 540
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 0.390625,
+      "learning_rate": 3.2983560316780104e-06,
+      "loss": 0.1849,
+      "step": 560
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 0.412109375,
+      "learning_rate": 2.9646731662242554e-06,
+      "loss": 0.184,
+      "step": 580
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.4140625,
+      "learning_rate": 2.6415287796261707e-06,
+      "loss": 0.1844,
+      "step": 600
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 0.412109375,
+      "learning_rate": 2.330596043105683e-06,
+      "loss": 0.1795,
+      "step": 620
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 0.4453125,
+      "learning_rate": 2.03348489862149e-06,
+      "loss": 0.1787,
+      "step": 640
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.39453125,
+      "learning_rate": 1.7517337229403946e-06,
+      "loss": 0.1781,
+      "step": 660
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 0.39453125,
+      "learning_rate": 1.4868013622576138e-06,
+      "loss": 0.1759,
+      "step": 680
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 0.404296875,
+      "learning_rate": 1.240059578609054e-06,
+      "loss": 0.178,
+      "step": 700
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.416015625,
+      "learning_rate": 1.012785947186397e-06,
+      "loss": 0.1785,
+      "step": 720
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 0.40234375,
+      "learning_rate": 8.061572413311253e-07,
+      "loss": 0.1778,
+      "step": 740
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 0.404296875,
+      "learning_rate": 6.212433394585865e-07,
+      "loss": 0.1771,
+      "step": 760
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.41796875,
+      "learning_rate": 4.590016854606727e-07,
+      "loss": 0.1756,
+      "step": 780
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 0.392578125,
+      "learning_rate": 3.2027233126997405e-07,
+      "loss": 0.1776,
+      "step": 800
+    },
+    {
+      "epoch": 2.73,
+      "grad_norm": 0.400390625,
+      "learning_rate": 2.057735872539157e-07,
+      "loss": 0.1764,
+      "step": 820
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.412109375,
+      "learning_rate": 1.1609830296019142e-07,
+      "loss": 0.1815,
+      "step": 840
+    },
+    {
+      "epoch": 2.87,
+      "grad_norm": 0.490234375,
+      "learning_rate": 5.1710797470987393e-08,
+      "loss": 0.1763,
+      "step": 860
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 0.400390625,
+      "learning_rate": 1.2944455259944476e-08,
+      "loss": 0.1788,
+      "step": 880
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.41015625,
+      "learning_rate": 0.0,
+      "loss": 0.1766,
+      "step": 900
+    },
+    {
+      "epoch": 3.0,
+      "step": 900,
+      "total_flos": 4.549145968838181e+18,
+      "train_loss": 0.20135066880120173,
+      "train_runtime": 71504.7155,
+      "train_samples_per_second": 2.411,
+      "train_steps_per_second": 0.013
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 900,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 10000,
+  "total_flos": 4.549145968838181e+18,
+  "train_batch_size": 24,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a563bdcff6ad918b048f8ad6209d18636cfd4e6ee497cb17a83424529219bdd6
+size 5048