AI-SOVEREIGN
Home / Open-source AI / safe-rlhf
Open-source AI

safe-rlhf

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

GitHub stars1.6K
Forks135
7d change–
LanguagePython
LicenseApache-2.0
Last commit24 Nov 2025
ai-safetyalpacabeaverdatasetsdeepspeedgptlarge-language-modelsllama

More from PKU-Alignment