uclaml / SPPO

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

Date Created 2024-06-13 (7 months ago)

Commits 28 (last one 8 days ago)

Stargazers 471 (6 this week)

Watchers 19 (0 this week)

Forks 47

License apache-2.0

Ranking

RepositoryStats indexes 609,425 repositories, of these uclaml/SPPO is ranked #97,075 (84th percentile) for total stargazers, and #117,481 for total watchers. Github reports the primary language for this repository as Python, for repositories using this language it is ranked #16,250/122,950.

uclaml/SPPO is also tagged with popular topics, for these it's ranked: deep-learning (#2,159/8640), large-language-models (#292/1131), fine-tuning (#55/196)

Other Information

uclaml/SPPO has 1 open pull request on Github, 3 pull requests have been merged over the lifetime of the repository.

Github issues are enabled, there are 14 open issues and 6 closed issues.

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

All Topics

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

Star History

Github stargazers over time

Watcher History

Github watchers over time, collection started in '23

Recent Commit History

28 commits on the default branch (main) since jan '22

Yearly Commits

Commits to the default branch (main) per year

Issue History

Languages

The primary language is Python but there's also others...

updated: 2025-01-30 @ 01:55pm, id: 814496416 / R_kgDOMIw6oA