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.

Merging fine-tuned models with mergekit v1.0.0

Use this resource to combine the abilities of several fine-tuned models without retraining

New

  • 424 downloads
  • 153 likes
  • 150 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install mergekit-model-merging

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 guides you through installing mergekit, writing a configuration file, then merging two models with linear interpolation or SLERP. It also presents TIES, DARE and task arithmetic, and production deployment.

Mostly picked by

Updated November 2, 2026

Card for the “Merging fine-tuned models with mergekit” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: installation, YAML configuration and linear or SLERP merge
  • references/methods.md, coefficient-tuning.md, examples.md and evaluation.md: methods, coefficient tuning, examples and evaluation

Good fit for

  • You want to combine a math model and a code model
  • You quickly test variants without training GPUs

Not for

    Tags

    • model merging
    • mergekit
    • slerp
    • llm

    About

    You say

    “Merge my two fine-tuned models with SLERP at equal weights, then evaluate the result.”

    Card for the “Merging fine-tuned models with mergekit” 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 combine the abilities of several fine-tuned models without retraining
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/coefficient-tuning.md14.7 KB
    • references/evaluation.md11.9 KB
    • references/examples.md9 KB
    • references/methods.md9.7 KB
    • SKILL.md13 KB

    Origin and licence

    Listed unmodified

    Author
    Orchestra Research
    Source
    github.com/orchestra-research/ai-research-skills/tree/773a52944ba4747a18bd4ae9ade53fff041adcbc/19-emerging-techniques/model-merging
    Licence
    MIT

    Notice

    « model-merging » (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.