Repository · GitHub

PKU-Alignment/safe-rlhf

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

Owner	PKU-Alignment
License (as declared)	Apache-2.0
Stars	1,619
Forks	134
Main language	Python
Created	15 May 2023
Last updated at source	24 November 2025

pythonai-safetyalpacabeaverdatasetsdeepspeedgptlarge-language-modelsllamallmllmsreinforcement-learningreinforcement-learning-from-human-feedbackrlhfsafe-reinforcement-learningsafe-reinforcement-learning-from-human-feedbacksafe-rlhfsafetytransformertransformersvicuna

Embed this entry

<iframe src="https://silytics.si/embed/item/c80b03ee-4639-41e4-88c9-664276d2217e" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

More from PKU-Alignment

align-anythingRepository
omnisafeRepository

Silytics shows public metadata from GitHub and links to the original. Information may be incomplete or out of date. Last refreshed 15 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.