Agent Skills: post-training-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.

ID: davila7/claude-code-templates/post-training-trl-fine-tuning

Install this agent skill to your local

npx skills add davila7/claude-code-templates --skill post-training-trl-fine-tuning

Skill Files

The files that make up post-training-trl-fine-tuning.

Download Skill

More agent skills