Instructions file CodexOpenCode
Instructions for stepfun-ai/SteptronOss, covering steptronoss agents, 1. working rules, self-improvement loop, 2. repo layout and utilities overview.
586 3mo ago A 5,675 tokens
original Apache-2.0
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.
Instructions file CodexOpenCode
Instructions for stepfun-ai/SteptronOss, covering steptronoss agents, 1. working rules, self-improvement loop, 2. repo layout and utilities overview.