Ai-research
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…
openrlhf-training is an Agent Skill — a folder with a SKILL.md and any helper scripts that a coding agent loads on demand. Drop it in your skills directory and the agent picks it up the next time the task matches.
Everything on this page — the summary, the category and the how-to — is written by HowToPrompts; the link below goes to the original project.
| Category | Ai-research |
|---|
/skill add openrlhf-trainingHow to use it
- Copy the skill folder into your agent's skills directory, or run the add command above.
- Reload the agent so it re-scans available skills.
- Trigger it by describing the task — the agent loads the skill when it matches.
Compiled and written by HowToPrompts from public sources.
← Back to Skills