verl
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexib
Also installable via skills CLI
npx skills add Orchestra-Research/AI-Research-SKILLs/06-post-training/verl
Source
Path:
06-post-training/verl/SKILL.md(main)