LightRFT: Light, Efficient, Omni-modal & Reward-model Driven Reinforcement Fine-Tuning Framework
opendilab/LightRFT is accelerating — star growth is speeding up by +0.7/day (69th percentile in the tracked cohort), on top of -0.1 stars/day.
Low breakout odds over the next 14 days, led by star acceleration (69th pctl). Confidence is high given the available history.
Transparent heuristic · logged for model training
Reconstructed from 155 snapshots — the time-series GitHub’s API doesn’t expose.
Live score, refreshed every 6 hours. Links back to this page.
[](https://repoclimb.com/repo/opendilab/LightRFT)Percentile rank within the tracked cohort. The score self-calibrates — it answers “accelerating vs. everything else,” not raw size.