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.

bishal-pdMSFT Updated 0 repo stars

File contents

bishal-pdMSFT/msb-skills commit 6041482448

Frequently asked questions

npx get-skill add bishal-pdmsft/fine-tuning-with-trl