stepfun-ai/
A lightweight, AI-native training framework for large language models. Designed for fast iteration, reproducible experiments, and modular configuration across SFT, RLVR, and evaluation workflows.
by stepfun-ai Python Apache-2.0 licence 47 forks Created Dec 2025 View on GitHub
- Stars
- 590
- 3% of stepfun-ai's stars
- Rank
- #108,283
- of 851,979 repos, top 13%
- In Python
- #19,982
- of 173,293 repos, top 12%
Among 851,979 repos
400–630 stars: 51,564 repos, including SteptronOss
top 50%top 10%top 1%top 0.1% 
Stars along the bottom, and repos in each band on a log scale
Quick stats
- Next rank
- +1 star to reach #108,116
- Next milestone
- +177 stars to reach the top 10%
- Popular
- One of 490,661 repos with 100+ stars