Community 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.

argentaios Updated 128 repo stars
ArgentOS

File contents

argentaios/argentos-core commit 0103204867

Frequently asked questions

npx get-skill add argentaios/community-fine-tuning-with-trl