model-finetuning

Features and purpose

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.

Quick start

Follow the repository instructions for this skill and your agent. Review the files and dependencies before adding it to your workflow.