@orchestra-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 DeepSpeedChat with distributed architecture and GPU resource sharing.
No skills found in this collection.
SKILL.md
Loading...
Select a file to preview
Analyzing security...
Checking scan reports and verification data.
Bill of Materials
Everything this skill can do — files, network, commands, and more.
No demos yet. To add one, ask your AI agent: "Submit a demo for @orchestra-research/openrlhf-training" — or upload via the API.
To add a demo, ask your AI agent: "Submit a demo for @orchestra-research/openrlhf-training"
No eval data yet. Eval results are published via the SkillSafe API.