~ / leaderboard / skill / openrlhf-training
Skill · #3598

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 DeepSpeedChat with distributed a

5rigs use it
0%of all rigs
7.4kavg rig context tax

Get it

$ npx degit Yichen-ZJU/lemvo/claude/skills/openrlhf .claude/skills/openrlhf-training

From the most-starred rig that ships it: Yichen-ZJU/lemvo. Same-named skills in different rigs may differ — review before use.

Often used together with

Rigs using openrlhf-training (5)

copied ✓