BetaRare
lsdefine/simple_GRPO
A very simple GRPO implement for reproducing r1-like LLM thinking.
- Owner
- lsdefine (personal account)
- Stars
- Stars: 1,719
- Forks
- Forks: 134
- Language
- Python
- License
- Apache-2.0
- Created
- 2025
- Tier
- Beta (700 to 1,999 ★) What this tier means
More repos by lsdefine
All 3 repos by lsdefine- lsdefine/GenericAgentStars: 14,382PythonStable
- lsdefine/attention-is-all-you-need-kerasStars: 720PythonBeta
Nearby in Python
All Python repos- scverse/scvi-toolsStars: 1,719PythonBeta
- unitreerobotics/xr_teleoperateStars: 1,719PythonBeta
- masamasa59/ai-agent-papersStars: 1,719PythonBeta
- heroku-python/flask-socketsStars: 1,718PythonBeta