Upload 12 files

README.md

@@ -0,0 +1,103 @@
+---
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/QwQ-32B-Preview/blob/main/LICENSE
+language:
+- en
+pipeline_tag: text-generation
+base_model: Qwen/Qwen2.5-32B-Instruct
+tags:
+- chat
+library_name: transformers
+---
+
+# QwQ-32B-Preview
+
+## Introduction
+
+**QwQ-32B-Preview** is an experimental research model developed by the Qwen Team, focused on advancing AI reasoning capabilities. As a preview release, it demonstrates promising analytical abilities while having several important limitations:
+
+1. **Language Mixing and Code-Switching**: The model may mix languages or switch between them unexpectedly, affecting response clarity.
+2. **Recursive Reasoning Loops**: The model may enter circular reasoning patterns, leading to lengthy responses without a conclusive answer.
+3. **Safety and Ethical Considerations**: The model requires enhanced safety measures to ensure reliable and secure performance, and users should exercise caution when deploying it.
+4. **Performance and Benchmark Limitations**: The model excels in math and coding but has room for improvement in other areas, such as common sense reasoning and nuanced language understanding.
+
+**Specification**:
+- Type: Causal Language Models
+- Training Stage: Pretraining & Post-training
+- Architecture: transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias
+- Number of Parameters: 32.5B
+- Number of Paramaters (Non-Embedding): 31.0B
+- Number of Layers: 64
+- Number of Attention Heads (GQA): 40 for Q and 8 for KV
+- Context Length: Full 32,768 tokens
+
+For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwq-32b-preview/). You can also check Qwen2.5 [GitHub](https://github.com/QwenLM/Qwen2.5), and [Documentation](https://qwen.readthedocs.io/en/latest/).
+
+## Requirements
+
+The code of Qwen2.5 has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`.
+
+With `transformers<4.37.0`, you will encounter the following error:
+```
+KeyError: 'qwen2'
+```
+
+## Quickstart
+
+Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "Qwen/QwQ-32B-Preview"
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+prompt = "How many r in strawberry."
+messages = [
+    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=512
+)
+generated_ids = [
+    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+]
+
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+```
+
+## Citation
+
+If you find our work helpful, feel free to give us a cite.
+
+```
+@misc{qwq-32b-preview,
+    title = {QwQ: Reflect Deeply on the Boundaries of the Unknown},
+    url = {https://qwenlm.github.io/blog/qwq-32b-preview/},
+    author = {Qwen Team},
+    month = {November},
+    year = {2024}
+}
+
+@article{qwen2,
+      title={Qwen2 Technical Report}, 
+      author={An Yang and Baosong Yang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Zhou and Chengpeng Li and Chengyuan Li and Dayiheng Liu and Fei Huang and Guanting Dong and Haoran Wei and Huan Lin and Jialong Tang and Jialin Wang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Ma and Jin Xu and Jingren Zhou and Jinze Bai and Jinzheng He and Junyang Lin and Kai Dang and Keming Lu and Keqin Chen and Kexin Yang and Mei Li and Mingfeng Xue and Na Ni and Pei Zhang and Peng Wang and Ru Peng and Rui Men and Ruize Gao and Runji Lin and Shijie Wang and Shuai Bai and Sinan Tan and Tianhang Zhu and Tianhao Li and Tianyu Liu and Wenbin Ge and Xiaodong Deng and Xiaohuan Zhou and Xingzhang Ren and Xinyu Zhang and Xipin Wei and Xuancheng Ren and Yang Fan and Yang Yao and Yichang Zhang and Yu Wan and Yunfei Chu and Yuqiong Liu and Zeyu Cui and Zhenru Zhang and Zhihao Fan},
+      journal={arXiv preprint arXiv:2407.10671},
+      year={2024}
+}
+```

config.json

@@ -0,0 +1,38 @@
+{
+    "architectures": [
+        "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 27648,
+    "max_position_embeddings": 32768,
+    "max_window_layers": 64,
+    "model_type": "qwen2",
+    "num_attention_heads": 40,
+    "num_hidden_layers": 64,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": 32768,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.43.1",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 152064,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.2.2",
+        "bits": 4.25,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 115,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "pad_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "repetition_penalty": 1.0,
+  "temperature": 0.7,
+  "top_p": 0.8,
+  "top_k": 20,
+  "transformers_version": "4.37.0"
+}

huggingface-metadata.txt

@@ -0,0 +1,21 @@
+url: https://huggingface.co/Qwen/QwQ-32B-Preview
+branch: main
+download date: 2024-11-28 00:42:29
+sha256sum:
+    ffebcb560a500f1984a7c694891a1354075ff7b7bb37e54b37c8b7d4e6e79d93 model-00001-of-00017.safetensors
+    5fa514bd1e90deb61c31efd64a9cf4a0375976c4c7cd996856c2d03b39664cd9 model-00002-of-00017.safetensors
+    9b651617538311cd1ba0919e3ab44b9e9373a523c89a30037942453f086b3952 model-00003-of-00017.safetensors
+    c1ad1cce832f86a2f63e59a080dc23548ddc31c68fc366d2b65048275fd92d74 model-00004-of-00017.safetensors
+    e0607b8dce4427d0310f06f9d853c50f0e00f2a3d4c020671187c499f7b795da model-00005-of-00017.safetensors
+    8d660bc6659c2f9672c52bbc28e88178c3eb55955fae8e5bc26563dca4fa8ffe model-00006-of-00017.safetensors
+    2dd54b23fe25c130ab6e407ade936382269fc177486475ea0de1132115542135 model-00007-of-00017.safetensors
+    81a100df124c214b152de6471a361015a8e03c2597f21e1471935d7365ed71a1 model-00008-of-00017.safetensors
+    a44110afb3ccce512e7c57c7c470240d3560c5dbf6939f2bcc6a8b0f96342fb7 model-00009-of-00017.safetensors
+    b50e2e937ae348f0eb3169d03020e1c9e6af9e163c7299d600104bf4e2a49a3f model-00010-of-00017.safetensors
+    8d915709803ae8717087e8bf7596ed10ef76e6943bc117148d46c2eb76d3dde4 model-00011-of-00017.safetensors
+    6487a04f25e7d6336c5de8f800337b31f060c11db9b042d4dd3becb86b0bfefa model-00012-of-00017.safetensors
+    123f52ba88a34a4832e59b5f428769eca4cb6495c6247e9e1d3cd86306a7db6a model-00013-of-00017.safetensors
+    a7e78d641e1164bd128d8f2b8d11f38bc3a985a774717db75b900f9a2596252b model-00014-of-00017.safetensors
+    170c30e3b020706e2ebd1fc9891256c9ca5859776542818a3e17efb5e979d4b8 model-00015-of-00017.safetensors
+    608fb9e35c12d2ce31bacc69a0c8175cb0c9582126cd6ab412f72ebfcf49b5f8 model-00016-of-00017.safetensors
+    3cc27c57a539b24b7c57b20553ad95c9a4582b086f9f3e7105445a126388cf13 model-00017-of-00017.safetensors

model.safetensors.index.json

@@ -0,0 +1,778 @@
+{
+  "metadata": {
+    "total_size": 65527752704
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00017-of-00017.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00017.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00017.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00017.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00004-of-00017.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00017.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00017.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00004-of-00017.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00004-of-00017.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00004-of-00017.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00017.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00017.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00017.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00017.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00017.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00017.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00005-of-00017.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00005-of-00017.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00005-of-00017.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00005-of-00017.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00005-of-00017.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00005-of-00017.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00005-of-00017.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00005-of-00017.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00005-of-00017.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00017.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00017.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00017.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00006-of-00017.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00006-of-00017.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00006-of-00017.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00017.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00017.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00017.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00006-of-00017.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00006-of-00017.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00006-of-00017.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00006-of-00017.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00006-of-00017.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00006-of-00017.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00006-of-00017.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00006-of-00017.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00006-of-00017.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00007-of-00017.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00007-of-00017.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00007-of-00017.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00007-of-00017.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00007-of-00017.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00007-of-00017.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00007-of-00017.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00007-of-00017.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00007-of-00017.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00007-of-00017.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00007-of-00017.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00007-of-00017.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00008-of-00017.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00008-of-00017.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00008-of-00017.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00008-of-00017.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00008-of-00017.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00008-of-00017.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00008-of-00017.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00008-of-00017.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00008-of-00017.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00008-of-00017.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00008-of-00017.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00008-of-00017.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00009-of-00017.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00009-of-00017.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00009-of-00017.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00009-of-00017.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00009-of-00017.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00009-of-00017.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00009-of-00017.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00009-of-00017.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00009-of-00017.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00009-of-00017.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00009-of-00017.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00009-of-00017.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00010-of-00017.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00010-of-00017.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00010-of-00017.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00010-of-00017.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00010-of-00017.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00010-of-00017.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00010-of-00017.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00010-of-00017.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00010-of-00017.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00010-of-00017.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00010-of-00017.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00010-of-00017.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00011-of-00017.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00011-of-00017.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00011-of-00017.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00011-of-00017.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00011-of-00017.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00011-of-00017.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00011-of-00017.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00011-of-00017.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00011-of-00017.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00011-of-00017.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00011-of-00017.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00011-of-00017.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00012-of-00017.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00012-of-00017.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00012-of-00017.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00012-of-00017.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00012-of-00017.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00012-of-00017.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00012-of-00017.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00012-of-00017.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00012-of-00017.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00012-of-00017.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00012-of-00017.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00012-of-00017.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00013-of-00017.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00013-of-00017.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00013-of-00017.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.48.self_attn.k_proj.bias": "model-00013-of-00017.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.48.self_attn.q_proj.bias": "model-00013-of-00017.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.48.self_attn.v_proj.bias": "model-00013-of-00017.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.49.self_attn.k_proj.bias": "model-00013-of-00017.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.49.self_attn.q_proj.bias": "model-00013-of-00017.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.49.self_attn.v_proj.bias": "model-00013-of-00017.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.50.self_attn.k_proj.bias": "model-00013-of-00017.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.50.self_attn.q_proj.bias": "model-00013-of-00017.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.50.self_attn.v_proj.bias": "model-00013-of-00017.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.51.self_attn.k_proj.bias": "model-00014-of-00017.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.51.self_attn.q_proj.bias": "model-00014-of-00017.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.51.self_attn.v_proj.bias": "model-00014-of-00017.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.52.self_attn.k_proj.bias": "model-00014-of-00017.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.52.self_attn.q_proj.bias": "model-00014-of-00017.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.52.self_attn.v_proj.bias": "model-00014-of-00017.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.53.self_attn.k_proj.bias": "model-00014-of-00017.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.53.self_attn.q_proj.bias": "model-00014-of-00017.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.53.self_attn.v_proj.bias": "model-00014-of-00017.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.54.self_attn.k_proj.bias": "model-00014-of-00017.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.54.self_attn.q_proj.bias": "model-00014-of-00017.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.54.self_attn.v_proj.bias": "model-00014-of-00017.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.55.self_attn.k_proj.bias": "model-00015-of-00017.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.55.self_attn.q_proj.bias": "model-00015-of-00017.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.55.self_attn.v_proj.bias": "model-00015-of-00017.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.56.self_attn.k_proj.bias": "model-00015-of-00017.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.56.self_attn.q_proj.bias": "model-00015-of-00017.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.56.self_attn.v_proj.bias": "model-00015-of-00017.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.57.self_attn.k_proj.bias": "model-00015-of-00017.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.57.self_attn.q_proj.bias": "model-00015-of-00017.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.57.self_attn.v_proj.bias": "model-00015-of-00017.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.58.self_attn.k_proj.bias": "model-00015-of-00017.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.58.self_attn.q_proj.bias": "model-00015-of-00017.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.58.self_attn.v_proj.bias": "model-00015-of-00017.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.59.self_attn.k_proj.bias": "model-00016-of-00017.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.59.self_attn.q_proj.bias": "model-00016-of-00017.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.59.self_attn.v_proj.bias": "model-00016-of-00017.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.60.self_attn.k_proj.bias": "model-00016-of-00017.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.60.self_attn.q_proj.bias": "model-00016-of-00017.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.60.self_attn.v_proj.bias": "model-00016-of-00017.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.61.self_attn.k_proj.bias": "model-00016-of-00017.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.61.self_attn.q_proj.bias": "model-00016-of-00017.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.61.self_attn.v_proj.bias": "model-00016-of-00017.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.62.self_attn.k_proj.bias": "model-00016-of-00017.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.62.self_attn.q_proj.bias": "model-00016-of-00017.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.62.self_attn.v_proj.bias": "model-00016-of-00017.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00017-of-00017.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00017-of-00017.safetensors",
+    "model.layers.63.self_attn.k_proj.bias": "model-00017-of-00017.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.63.self_attn.q_proj.bias": "model-00017-of-00017.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.63.self_attn.v_proj.bias": "model-00017-of-00017.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00017.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00017.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00017.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00017.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00017.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00017.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00017.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00017.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00017.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+    "model.norm.weight": "model-00017-of-00017.safetensors"
+  }
+}

output-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a05b1ac52e9f14b6b234886a5ace83e7a3d4bf267dd4a3ad08a6ddcea941cf41
+size 8545220170

output-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9b0fb783b58dfc0ac3105cceb051e50941662b46f2cd41d5a919b46cbac8fcd
+size 8520457780

output-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68a2b8598e7b7b9ebe9d6ea10c4fe9549c5af7afdc48e4d2a915c0768ef12778
+size 1681771120

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "add_bos_token": false
+}