ReaLHF
Super-Efficient RLHF Training of LLMs with Parameter Reallocation
openpsi-project/ReaLHF
View on GitHub ↗Super-Efficient RLHF Training of LLMs with Parameter Reallocation
ReaLHF grew +0.0% in the last 30 days, ranks 39th of 82 in Reinforcement Learning / RLHF, last commit 549 days ago.
Star trajectory
115 days tracked2026-07-02336 stars today2026-10-25
Momentum
+0.0% in 30d, below the Reinforcement Learning / RLHF median of +1.1%.
Maintenance
Last commit 549 days ago, staler than the median of 46d.
How it compares in Reinforcement Learning / RLHF
ReaLHF
336
stars
+0.0% 30d
commit 549 days ago
Reinforcement Learning / RLHF median
309
stars
+1.1% 30d
commit ~46d ago
Leader · OpenRLHF
10.1k
stars
+0.7% 30d
commit 19 days ago
Ranked 39th of 82 by stars.
ZJU-REAL/SDAR373-37alphadl/AdaRubrics367-31
openpsi-project/ReaLHF336
accel-brain/accel-brain-code328+8NVlabs/ENPIRE311+25- Language
- Python
- License
- Apache License 2.0
- Contributors
- 3
- Forks
- 22
- Watchers
- 1
- Open issues
- 0
- Releases
- 2
- Created
- 2024-06-18
- Stars this week
- +0
You've seen where ReaLHF 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.