Modelpublic

SiningZhou/Qwen3-8B-VM

sourceHugging Facemitupdated 1y agoView on Hugging Face

0likes13downloads

Model Card

Model Card for Qwen3-8B-VM

This model is the value model trained with the ReST-RL paradigm, based on the Qwen3-8B model. It is recommended to use this model in conjunction with the ReST-RL finetuned model to attain optimal results.

Framework versions

—TRL: 0.19.1
—Transformers: 4.51.3
—Pytorch: 2.6.0
—Datasets: 3.2.0
—Tokenizers: 0.21.1

Citations

Cite ReST-RL as:

bibtex

@misc{zhoubian2025restrlachievingaccuratecode,
      title={ReST-RL: Achieving Accurate Code Reasoning of LLMs with Optimized Self-Training and Decoding}, 
      author={Sining Zhoubian and Dan Zhang and Jie Tang},
      year={2025},
      eprint={2508.19576},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2508.19576}, 
}