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.

agentic-in Updated 586 repo stars
Elephant Agent follows a personal path with people, places, risks, rhythms, decisions, and a Personal Model

File contents

agentic-in/elephant-agent commit 47c8087218

Frequently asked questions

npx get-skill add agentic-in/trl-fine-tuning