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.

Preference alignment with SimPO v1.0.0

Use this resource to align a model on preferences without a reference model

New

  • 499 downloads
  • 163 likes
  • 152 saves

Free

Install with the CLI

In a terminal, from the folder you want:

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

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 prepares a preference dataset, tunes the hyperparameters and runs SimPO training, with a starter recipe on a model such as Mistral 7B. You get an aligned model without the second reference model that DPO requires.

Mostly picked by

Updated November 2, 2026

Card for the “Preference alignment with SimPO” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: installation, training procedure and basic workflow
  • references/: datasets, hyperparameters and loss functions

Good fit for

  • You want to align a model without loading a reference model
  • You have pairs of preferred and rejected responses

Not for

    Tags

    • alignment
    • preferences
    • llm
    • training
    • dpo

    About

    You say

    “Align this model on my preferred and rejected response pairs with SimPO.”

    Card for the “Preference alignment with SimPO” skill

    Skill published by Orchestra Research 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 model on preferences without a reference model
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/datasets.md10.6 KB
    • references/hyperparameters.md8.3 KB
    • references/loss-functions.md6.9 KB
    • SKILL.md5.6 KB

    Origin and licence

    Listed unmodified

    Author
    Orchestra Research
    Source
    github.com/nousresearch/hermes-agent/tree/0c74cc682dc81bf78b78a1737b3ee77a820ccb79/optional-skills/mlops/simpo
    Licence
    MIT

    Notice

    « simpo » (Orchestra Research, 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.