Liang0223's picture
Add model card (#1)
fbfb840 verified
metadata
license: mit
library_name: transformers
pipeline_tag: text-generation

This model was presented in the paper On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification.

Code: https://github.com/yongliang-wu/DFT?tab=readme-ov-file