Download

Skill UI

Browse and discover 5019+ curated skills

All Development Artificial Intelligence Design & Creative Product & Business Data Science Marketing Soft Skills Productivity Engineering Languages

Search RLHF , found 3 results

Default Newest Most Downloaded

TRL Reinforcement Fine-Tuning

fine-tuning-with-trl

Orchestra-Research/AI-Research-SKILLs

Provides TRL-based RLHF fine-tuning flows covering SFT, reward-model training, PPO, DPO, and GRPO so teams can align HuggingFace models with preferences using both pipeline scripts and CLI helpers.

OpenRLHF High Performance Training

openrlhf-training

Orchestra-Research/AI-Research-SKILLs

OpenRLHF is a Ray-based RLHF framework that accelerates large-model PPO, GRPO, RLOO, and DPO training with vLLM inference and ZeRO-3 resource sharing, targeting distributed GPU clusters handling 7B-70B+ parameter models.

Verl RL Training

verl-rl-training

Orchestra-Research/AI-Research-SKILLs

Guides RLHF-style LLM fine-tuning with verl's HybridFlow stack, scaling PPO/GRPO/DAPO across FSDP/Megatron/vLLM backends for math reasoning, agentic multiturn, and vision-language workflows.

1

Language