Trl Training

Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training via CLI commands.

Hugging Face Updated 11.4k repo stars

File contents

huggingface/skills commit a89ae0d1da

Frequently asked questions

npx get-skill add huggingface/trl-training-2