PrototypeCommon
qwenpilot/FIPO
This code implements the algorithm of FIPO, a value-free RL recipe for eliciting deeper reasoning from a clean base model.
- Owner
- qwenpilot (personal account)
- Stars
- Stars: 129
- Forks
- Forks: 6
- Language
- Python
- License
- Apache-2.0
- Created
- 2026
- Topics
- llm-trainingpost-trainingreasoning-language-modelsreinforcement-learning-algorithms
- Tier
- Prototype (100 to 249 ★) What this tier means
Nearby in Python
All Python repos- ReckyStar/mcd-party-plannerStars: 129PythonPrototype
- Gamma-Robot/bfm_ttcStars: 129PythonPrototype
- sanjayadanushka712/Ghost-NightStars: 129PythonPrototype
- ralsina/pyqt-by-exampleStars: 129PythonPrototype
- brosner/everyblock_codeStars: 129PythonPrototype
- marook/tagfsStars: 129PythonPrototype