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.
1 file for Codex and OpenCode: SteptronOss AGENTS.md — 5,675 tokens loaded in every session.
AGENTS.md A 5,675 tok These files are stepfun-ai/SteptronOss's own configuration — they tell Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.