vibehacker

Preference Optimization

Skill

Align models with preference data using DPO, ORPO, KTO or SimPO

by wshobson Listed Jul 24, 2025

Clone or download it from github.com, then drop the folder into ~/.claude/skills/ (Claude Code) or your agent's skills directory.

Product badge

Share this product's name and rating in your README or on your website.

Preference Optimization: rating on VibeHacker

Updates may be delayed by image caching.

Preference Optimization cover

About Preference Optimization

A wshobson/agents skill for aligning a fine-tuned model once you have preference pairs or thumbs-up/down feedback. It compares methods and helps with hyperparameters and debugging DPO runs.

Used Preference Optimization?

Log in to write a review.

No reviews yet

Used it? Write the first review.