voidful / TextRL

Implementation of ChatGPT RLHF (Reinforcement Learning with Human Feedback) on any generation model in huggingface's transformer (blommz-176B/bloom/gpt/bart/T5/MetaICL)

Date Created 2021-03-18 (3 years ago)

Commits 70 (last one 6 months ago)

Stargazers 542 (0 this week)

Watchers 11 (0 this week)

Forks 60

License mit

Ranking

RepositoryStats indexes 579,238 repositories, of these voidful/TextRL is ranked #84,714 (85th percentile) for total stargazers, and #190,577 for total watchers. Github reports the primary language for this repository as Python, for repositories using this language it is ranked #13,748/115,001.

voidful/TextRL is also tagged with popular topics, for these it's ranked: pytorch (#1,303/5908), chatgpt (#556/2493), nlp (#538/2392), reinforcement-learning (#281/1293), gpt-3 (#120/589), language-model (#132/500)

Other Information

voidful/TextRL has 1 open pull request on Github, 2 pull requests have been merged over the lifetime of the repository.

Github issues are enabled, there are 3 open issues and 20 closed issues.

All Topics

nlg nlp rlhf gpt-2 gpt-3 chatgpt pytorch controlled-nlg language-model reinforcement-learning

Star History

Github stargazers over time

Watcher History

Github watchers over time, collection started in '23

Recent Commit History

52 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: 2024-11-06 @ 01:24am, id: 349008051 / R_kgDOFM1wsw