Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Aligning a model on preferences: DPO, ORPO, KTO v1.0.0

Use this resource to align a fine-tuned model on preference pairs

New

  • 395 downloads
  • 222 likes
  • 181 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install dpo-preference-alignment

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent picks the preference-optimisation method that fits your data, builds pairs from outcomes and tunes the hyperparameters of a DPO run. It also helps debug a run that stalls.

Mostly picked by

Updated November 2, 2026

Card for the “Aligning a model on preferences: DPO, ORPO, KTO” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: method choice, iterative production and pair construction
  • references/method-configs.md: DPO, ORPO, KTO and SimPO configurations

Good fit for

  • You have preferred and rejected pairs
  • Your thumbs-up and thumbs-down feedback should feed training

Not for

    Tags

    • dpo
    • preferences
    • alignment
    • fine-tuning

    About

    You say

    “Choose between DPO and KTO for our thumbs-up and thumbs-down feedback, then write the config.”

    Card for the “Aligning a model on preferences: DPO, ORPO, KTO” skill

    Skill published by wshobson under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to align a fine-tuned model on preference pairs
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/method-configs.md6.7 KB
    • SKILL.md7.9 KB

    Origin and licence

    Listed unmodified

    Author
    wshobson
    Source
    github.com/wshobson/agents/tree/0874a27b17a22e2b7c2e2bcd725768e0803cad06/plugins/llm-finetuning/skills/preference-optimization
    Licence
    MIT

    Notice

    « preference-optimization » (wshobson, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.