~ / skills / productivity / openrlhf-training

openrlhf-training

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than…

Industry: productivity
License: Unverified
Source repo: Orchestra-Research/AI-Research-SKILLs · ★ 10,718
Source file: 06-post-training/openrlhf/SKILL.md

View full SKILL.md on GitHub →

不会安装？看中文图文教程 →