ELYZA Shortcut 1.0 Qwen 32B

🚀 ELYZA-Shortcut-1.0-Qwen-32B

ELYZA-Shortcut-1.0-Qwen-32B 是在推理模型 ELYZA-Thinking-1.0-Qwen-32B 开发过程中衍生出的非推理模型。该模型基于 Qwen/Qwen2.5-32B-Instruct，经过后续训练，可绕过逐步推理过程，直接生成最终答案（基于通义千问构建）。

🚀 快速开始

本模型可结合 Hugging Face Transformers 库使用。以下是使用该模型进行推理的示例代码：

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "elyza/ELYZA-Shortcut-1.0-Qwen-32B"
prompt = "仕事の熱意を取り戻すためのアイデアを5つ挙げてください。"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto",
)
model.eval()
messages = [{"role": "user", "content": prompt}]
input_text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
token_ids = tokenizer.encode(
    input_text, add_special_tokens=False, return_tensors="pt"
)
with torch.no_grad():
    output_ids = model.generate(
        token_ids.to(model.device),
        max_new_tokens=8192,
        do_sample=True,
        temperature=0.6,
        top_p=0.95,
    )
output = tokenizer.decode(
    output_ids.tolist()[0][token_ids.size(1):], skip_special_tokens=True
)
print(output)

对于模型部署，建议使用 vLLM 创建兼容 OpenAI 的服务器，示例命令如下：

vllm serve elyza/ELYZA-Shortcut-1.0-Qwen-32B \
    --tensor-parallel-size 8 \
    --max-model-len 32768

✨ 主要特性

在后续训练阶段，该模型使用问题 - 解决方案对进行有监督微调（SFT）训练。这些问题 - 解决方案对是通过基于蒙特卡罗树搜索（MCTS）的算法探索出最优推理路径后，去除推理步骤得到的。更多详细信息，请参考 我们的博客文章。

💻 使用示例

基础用法

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "elyza/ELYZA-Shortcut-1.0-Qwen-32B"
prompt = "仕事の熱意を取り戻すためのアイデアを5つ挙げてください。"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto",
)
model.eval()
messages = [{"role": "user", "content": prompt}]
input_text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
token_ids = tokenizer.encode(
    input_text, add_special_tokens=False, return_tensors="pt"
)
with torch.no_grad():
    output_ids = model.generate(
        token_ids.to(model.device),
        max_new_tokens=8192,
        do_sample=True,
        temperature=0.6,
        top_p=0.95,
    )
output = tokenizer.decode(
    output_ids.tolist()[0][token_ids.size(1):], skip_special_tokens=True
)
print(output)

高级用法

vllm serve elyza/ELYZA-Shortcut-1.0-Qwen-32B \
    --tensor-parallel-size 8 \
    --max-model-len 32768

📚 详细文档

引用方式

@misc{elyza2025thinking,
    title={elyza/ELYZA-Thinking-1.0-Qwen-32B},
    url={https://huggingface.co/elyza/ELYZA-Thinking-1.0-Qwen-32B},
    author={Masato Hirakawa and Tomoaki Nakamura and Akira Sasaki and Daisuke Oba and Shoetsu Sato},
    year={2025},
}

参考文献

@misc{qwen2.5,
    title = {Qwen2.5: A Party of Foundation Models},
    url = {https://qwenlm.github.io/blog/qwen2.5/},
    author = {Qwen Team},
    month = {September},
    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}
}

📄 许可证

本项目采用 apache-2.0 许可证。

📦 模型信息