BetaRare
policy-gradient/GRPO-Zero
Implementing DeepSeek R1's GRPO algorithm from scratch
- Owner
- policy-gradient (organization)
- Stars
- Stars: 1,911
- Forks
- Forks: 103
- Language
- Python
- License
- Apache-2.0
- Created
- 2025
- Tier
- Beta (700 to 1,999 ★) What this tier means
Nearby in Python
All Python repos- qqfly/how-to-learn-roboticsStars: 1,911PythonBeta
- m4ll0k/BBTzStars: 1,911PythonBeta
- FACEGOOD/FACEGOOD-Audio2FaceStars: 1,911PythonBeta
- thampiman/reverse-geocoderStars: 1,911PythonBeta
- johnwheeler/flask-askStars: 1,911PythonBeta