Qwen3-0.6B-Timber

Qwen3-0.6B-Timber

<p align="center"> <img src="https://raw.githubusercontent.com/wutaiqiang/Timber/refs/heads/main/asset/logo_yrm.png" width="30%"> <br> </p>

Official weights for paper Timber: Training-free Instruct Model Refining with Base via Effective Rank

<a href="https://huggingface.co/collections/taki555/timber-68db45e4f4c64c1bfe52b492"><b>[🤗 HF Models]</b></a> • <a href="https://arxiv.org/abs/2509.23595"><b>[📜 Paper]</b></a> • <a href="https://github.com/wutaiqiang/Timber"><b>[🐱 GitHub]</b></a>

Please check our paper for more details.

☕️ Citation

If you find this repository helpful, please consider citing our paper:

@article{wu2025timber,
  title={Timber: Training-free Instruct Model Refining with Base via Effective Rank},
  author={Wu, Taiqiang and Yang, Runming and Liu, Tao and Wang, Jiahao and Xu, Zenan and Wong, Ngai.},
  journal={arXiv preprint arXiv:2509.23595},
  year={2025}
}

For any questions, please pull an issue or email at [email protected]