LightOnOCR-2 🦉 Collection LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family • 12 items • Updated 7 days ago • 23
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization Paper • 2601.05242 • Published Jan 8 • 230
mlx-community/functiongemma-270m-it-bf16 Text Generation • 0.3B • Updated Dec 18, 2025 • 231 • 7