safe-rlhf
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
PKU-Alignment/safe-rlhf
View on GitHub ↗Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
safe-rlhf grew +0.1% in the last 30 days, ranks 8th of 82 in Reinforcement Learning / RLHF, last commit 333 days ago.
Star trajectory
113 days tracked2026-07-021.6k stars today2026-10-23
Momentum
+0.1% in 30d, below the Reinforcement Learning / RLHF median of +1.1%.
Maintenance
Last commit 333 days ago, staler than the median of 44d.
How it compares in Reinforcement Learning / RLHF
safe-rlhf
1.6k
stars
+0.1% 30d
commit 333 days ago
Reinforcement Learning / RLHF median
306
stars
+1.1% 30d
commit ~44d ago
Leader · OpenRLHF
10.1k
stars
+0.7% 30d
commit 17 days ago
Ranked 8th of 82 by stars.
AgentR1/Agent-R11.7k-85TokenRhythm/NeoHorse1.7k-71
PKU-Alignment/safe-rlhf1.6k
RLHFlow/RLHF-Reward-Modeling1.5k+75uclaml/SPIN1.3k+366- Language
- Python
- License
- Apache License 2.0
- Contributors
- 4
- Forks
- 134
- Watchers
- 15
- Open issues
- 17
- Releases
- 0
- Created
- 2023-05-15
- Stars this week
- +0
You've seen where safe-rlhf stands today.
Get the moves before everyone else: the 5 Reinforcement Learning / RLHF repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.