AlphaUncommon
opendilab/LightRFT
LightRFT: Light, Efficient, Omni-modal & Reward-model Driven Reinforcement Fine-Tuning Framework
- Owner
- opendilab (organization)
- Stars
- Stars: 390
- Forks
- Forks: 12
- Language
- Python
- License
- Apache-2.0
- Created
- 2025
- Topics
- dapogrpollmllm-trainingmulti-modalreinforcement-learningrftreward-modelvlm
- Tier
- Alpha (250 to 699 ★) What this tier means
More repos by opendilab
All 43 repos by opendilab- opendilab/awesome-RLHFStars: 4,438RC
- opendilab/DI-engineStars: 3,649PythonRC
- opendilab/PPOxFamilyStars: 2,625PythonRC
- opendilab/LightZeroStars: 1,659PythonBeta
- opendilab/awesome-diffusion-model-in-rlStars: 1,654Beta
- opendilab/DI-starStars: 1,405PythonBeta
Nearby in Python
All Python repos- barckley75/resolve-claude-mcpStars: 390PythonAlpha
- moss-site/moss-trade-bot-skillsStars: 390PythonAlpha
- eddyzzl/marvis-risk-agentStars: 390PythonAlpha
- kroger/pyknonStars: 390PythonAlpha
- Moo-Ack-Productions/MCprepStars: 390PythonAlpha
- hMatoba/PiexifStars: 390PythonAlpha