Trl Fine Tuning

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.

graniet Updated 213 repo stars

File contents

graniet/kheish commit c67b8301ad

Frequently asked questions

npx get-skill add graniet/trl-fine-tuning