Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
- ai-safety
- alpaca
- datasets
- deepspeed
Repository Index
81,588 visible repositories in the index
1–1 of 1 · Most stars
81,588 visible repositories in the index
1–1 of 1 · Most stars
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback