uclaml/SPPO

The official implementation of Self-Play Preference Optimization (SPPO)

⭐ 589 ⑂ 48 Python Apache-2.0 · 2025-01-23推送

https://uclaml.github.io/SPPO/

deep-learning fine-tuning large-language-models rlhf self-play

589

Watchers

0

贡献者

0

Commits

0

Releases

15

Open Issues

2025-01-23

最近推送

原文中文

暂无 README