Huggingface 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.

pyfagorass Updated 2 repo stars

File contents

pyfagorass/bookofspells commit d1b3ea48b8

Frequently asked questions

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