Add AI-MO/qwen2-72b-sft-aimo_v03.00 checkpoint

README.md

@@ -0,0 +1,68 @@
+---
+base_model: AI-MO/qwen2-72b-sft
+tags:
+- alignment-handbook
+- generated_from_trainer
+datasets:
+- AI-MO/numina-dataset-tora-v1.0-release-candidate-1
+model-index:
+- name: qwen2-72b-sft-aimo_v03.00
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/huggingface/h4/runs/bxdbewkc)
+# qwen2-72b-sft-aimo_v03.00
+
+This model is a fine-tuned version of [AI-MO/qwen2-72b-sft](https://huggingface.co/AI-MO/qwen2-72b-sft) on the AI-MO/numina-dataset-tora-v1.0-release-candidate-1 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4792
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 32
+- total_train_batch_size: 32
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.3939        | 1.0   | 797  | 0.3793          |
+| 0.2618        | 2.0   | 1594 | 0.3876          |
+| 0.1141        | 3.0   | 2391 | 0.4310          |
+| 0.0363        | 4.0   | 3188 | 0.4792          |
+
+
+### Framework versions
+
+- Transformers 4.42.3
+- Pytorch 2.3.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 4.0,
+    "eval_loss": 0.47916728258132935,
+    "eval_runtime": 2.3746,
+    "eval_samples": 99,
+    "eval_samples_per_second": 14.739,
+    "eval_steps_per_second": 0.842,
+    "perplexity": 1.6147292290406077,
+    "total_flos": 2680278636036096.0,
+    "train_loss": 0.20304497943459596,
+    "train_runtime": 21214.9362,
+    "train_samples": 72441,
+    "train_samples_per_second": 4.806,
+    "train_steps_per_second": 0.15
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "AI-MO/qwen2-72b-sft",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 29568,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 80,
+  "model_type": "qwen2",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "eval_loss": 0.47916728258132935,
+    "eval_runtime": 2.3746,
+    "eval_samples": 99,
+    "eval_samples_per_second": 14.739,
+    "eval_steps_per_second": 0.842,
+    "perplexity": 1.6147292290406077
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.42.3"
+}

model-00001-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90d6b00a02389f729471b650addb117d54bcf55df016238b385e94b05be32685
+size 4548798728

model-00002-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6baa709ee5138804f9d2b0045a3af475c0b82f8bedaa57b93e299e896b15dcf4
+size 4964101384

model-00003-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:937382328a2ad2d56f6aa2cab7805ba636c81640e7aa62de447b4b2533661650
+size 4781637328

model-00004-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b677682ccee15f980e85f457db46df426cad6680c14983e96ec3dba4a23bdbf5
+size 4781670320

model-00005-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8a00910a2fd77985b6f6bcc55ad0fa502779d5d57c1c9b69e4033215cc5fdc9
+size 4781670360

model-00006-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f17a2b65f8d3a78e25e0d72b5f93f82df8f091fef9f6cac96a5fa4c051dc98c
+size 4964101416

model-00007-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82961f8fb71632a41ea922f67cf2e980a338f3b1bf826527a1ab7ebe35f945df
+size 4781637360

model-00008-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1992786669488fd85dcdbcc07b219bf9d1b9173048898c0ecf0404b8fe93f997
+size 4781670360

model-00009-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91493d23f89d6a91e4254768114b4e9b8f06cfda36ac0f4cc339feb29e54a60e
+size 4781670360

model-00010-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a676e9ceb7f13435322e05bce474d19cd3dd45dde4a2cc8519bb6ab5aacfbb1
+size 4964101416

model-00011-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb99c46cad110f02e359b7e3ed53bc2c28f3c9df9f781b9b9d7426e6ddb72b9d
+size 4781637360

model-00012-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88df77abc01f4e9aee358c60eb02003ab6a53381c3f6a34e55b9446c8a791e90
+size 4781670360

model-00013-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b58111a93c60278fe0c55d24c507fc8fd6ec9681b9c43154802bfc24611ca23e
+size 4781670360

model-00014-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:900cf2b30965bf604ad25a3fa5b9b5784a6452e4512b182562b3d89cff0aae9c
+size 4964101416

model-00015-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00b0dde18ee5b73b982a4a03daa72ba08b6c0cd8900502bc1a9c867168888f1c
+size 4781637360

model-00016-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22cee7d3c48da1eba371c6c1aa206fc6c8693858b3f1c554c2fac2e12aa26395
+size 4781670360

model-00017-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36bb2e928d6e591a762b0ab96010751f5b9b6249503e9a12f430f6b883cfa4c4
+size 4781670360

model-00018-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45848bfd2a444aba5ba93b94b2bef494bcfdef7cbf38dc5896721e76afb60417
+size 4964101416

model-00019-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60dcdceea9406c9c842d8a39c9b4063a461264fcd5bac4500312eabec62c2243
+size 4781637360

model-00020-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:648b6717632cf9f8d74c40e3d65f5ed63620ebbd28720e64ac363487a5e90de3
+size 4781670360

model-00021-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8bc92d4a1433a1cac919444cf42dd9999f19523146cc0f3cc644a484edce7be
+size 4781670360

model-00022-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a9aa720b79b707669b1028c305741e8a1dcbb977bc44092fd13c2104c8fd528
+size 4964101416

model-00023-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab3f63a938470f10b592b3d4b3f047fe27da54edacf1f2942582ea04bc4a5652
+size 4781637360

model-00024-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b79716040f5a6e40fe4352fea068d2bfaf8e0af6517236179344703a8986431e
+size 4781670360

model-00025-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:166cd7bc418a07d5803d18bb519f1dad9b142b35156bf585052af1b580ee3d93
+size 4781670360

model-00026-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d7f483523544ce15d1a7bdd5fdfee70201fa4e3375d9026a1570576695734c8
+size 4964101416

model-00027-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9584d9b7780e5a3ba02d178cc5ff554fb11b65652125bd9508d0498a0aebbbe7
+size 4781637360

model-00028-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c2eec84d98dacbfd8faf841980eedd88948bdc19dc17926b2e522ff39312b28
+size 4781670360

model-00029-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87d6204b5bdf145a82bb27b5fbf4fe8f82709cff0b0b62b7bbc25a29d9c89ee0
+size 4781670360

model-00030-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:705cd7d293f5267150cc704df3503a610ac02d5c7afa8ab692da86e24c6285f7
+size 3208747032

model-00031-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e47701663a7f31665841be241024908754d9aa0bc1c43608790b32051b7b52e
+size 2491416704

model.safetensors.index.json

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

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if (message['role'] == 'system')%}{{ '' }}{% elif (message['role'] == 'user')%}{{ '### Problem: ' + message['content'] + '\n' }}{% elif (message['role'] == 'assistant')%}{{ '### Solution: ' + message['content'] + '\n' }}{% endif %}{% if loop.last and message['role'] == 'user' and add_generation_prompt %}{{ '### Solution: ' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "total_flos": 2680278636036096.0,
+    "train_loss": 0.20304497943459596,
+    "train_runtime": 21214.9362,
+    "train_samples": 72441,
+    "train_samples_per_second": 4.806,
+    "train_steps_per_second": 0.15
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55bdb1e17a10d5639a2e0e5a9f8ce1db2918475ef4c4e27ce1e3eeb8e6a55acc
+size 7480