FIPO
This code implements the algorithm of FIPO, a value-free RL recipe for eliciting deeper reasoning from a clean base model.
qwenpilot/FIPO
View on GitHub ↗This code implements the algorithm of FIPO, a value-free RL recipe for eliciting deeper reasoning from a clean base model.
FIPO grew -0.8% in the last 30 days, ranks 68th of 82 in Reinforcement Learning / RLHF, last commit 202 days ago.
Star trajectory
116 days tracked2026-07-02129 stars today2026-10-26
Momentum
-0.8% in 30d, below the Reinforcement Learning / RLHF median of +1.1%.
Maintenance
Last commit 202 days ago, staler than the median of 47.5d.
How it compares in Reinforcement Learning / RLHF
FIPO
129
stars
-0.8% 30d
commit 202 days ago
Reinforcement Learning / RLHF median
310.5
stars
+1.1% 30d
commit ~47.5d ago
Leader · OpenRLHF
10.1k
stars
+0.7% 30d
commit 20 days ago
Ranked 68th of 82 by stars.
- Language
- Python
- License
- Apache License 2.0
- Contributors
- 1
- Forks
- 6
- Watchers
- 0
- Open issues
- 1
- Releases
- 0
- Created
- 2026-03-22
- Stars this week
- -1
You've seen where FIPO 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.