Fine Tuning With Trl

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

deepleaper Updated 7 repo stars

File contents

deepleaper/leaper-agent commit 70023fc707

Frequently asked questions

npx get-skill add deepleaper/fine-tuning-with-trl