taki555/Llama3.1-8B-Shadow-FT-BAAI-2k

Shadow-FT

[📜 Paper] • [🤗 HF Models] • [🐱 GitHub]

This repo contains the weights from our paper: Shadow-FT: Tuning Instruct via Base by Taiqiang Wu* Runming Yang*, Jiayi Li, Pengfei Hu, Ngai Wong and Yujiu Yang.

* for equal contributions.

Overview

Observation:

• Directly tuning the INSTRUCT (i.e., instruction tuned) models often leads to marginal improvements and even performance degeneration.

• Paired BASE models, the foundation for these INSTRUCT variants, contain highly similar weight values (i.e., less than 2% on average for Llama 3.1 8B).

$\Rightarrow$ We propose the Shadow-FT framework to tune the INSTRUCT models by leveraging the corresponding BASE models. The key insight is to fine-tune the BASE model, and then directly graft the learned weight updates to the INSTRUCT model.

Performance

This repository contains the Llama-3.1-8B tuned on BAAI-2k subsets using Shadow-FT.

please refer to our paper for details.

☕️ Citation

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

@article{wu2025shadow,
  title={Shadow-FT: Tuning Instruct via Base},
  author={Wu, Taiqiang and Yang, Runming and Li, Jiayi and Hu, Pengfei and Wong, Ngai and Yang, Yujiu},
  journal={arXiv preprint arXiv:2505.12716},
  year={2025}
}

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