0.2.8
版本发布时间: 2024-02-19 10:20:36
lucidrains/self-rewarding-lm-pytorch最新发布版本:0.2.12(2024-04-11 09:09:42)
What's Changed
- Fix TypeError for is_valid_reward in SelfRewardDPOConfig by @ViswanathaReddyGajjala in https://github.com/lucidrains/self-rewarding-lm-pytorch/pull/19
New Contributors
- @ViswanathaReddyGajjala made their first contribution in https://github.com/lucidrains/self-rewarding-lm-pytorch/pull/19
Full Changelog: https://github.com/lucidrains/self-rewarding-lm-pytorch/compare/0.2.7...0.2.8