openpsi-project / ReaLHF

Super-Efficient RLHF Training of LLMs with Parameter Reallocation

Date Created 2024-06-18 (10 months ago)

Commits 1,078 (last one 3 months ago)

Stargazers 277 (4 this week)

Watchers 5 (0 this week)

Forks 17

License apache-2.0

Ranking

RepositoryStats indexes 639,263 repositories, of these openpsi-project/ReaLHF is ranked #149,317 (77th percentile) for total stargazers, and #325,936 for total watchers. Github reports the primary language for this repository as Python, for repositories using this language it is ranked #26,587/131,078.

openpsi-project/ReaLHF is also tagged with popular topics, for these it's ranked: llm (#1,258/3695), reinforcement-learning (#462/1471), large-language-models (#458/1258), transformers (#315/906), distributed-systems (#276/578), distributed-computing (#77/198)

Other Information

openpsi-project/ReaLHF has 1 open pull request on Github, 69 pull requests have been merged over the lifetime of the repository.

Github issues are enabled, there are 6 open issues and 18 closed issues.

There have been 2 releases, the latest one was published on 2024-09-05 (7 months ago) with the name v0.3.0.

All Topics

llm deepspeed megatron-lm llm-training transformers llm-framework distributed-systems distributed-computing large-language-models reinforcement-learning large-scale-machine-learning reinforcement-learning-from-human-feedback

Star History

Github stargazers over time

Watcher History

Github watchers over time, collection started in '23

Recent Commit History

1,078 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: 2025-04-15 @ 01:48pm, id: 816579552 / R_kgDOMKwD4A