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.

Exporting a fine-tuned model to a deployment format v1.0.0

Use this resource to export a fine-tuned model in the format suited to its target

New

  • 517 downloads
  • 248 likes
  • 196 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install fine-tuned-model-export

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

Once the checkpoint is validated, the agent picks the format for the hardware target and serving stack, runs the export and performs a smoke test. Any pre- and post-export mismatch blocks delivery.

Mostly picked by

Updated November 2, 2026

Card for the “Exporting a fine-tuned model to a deployment format” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: format map, typical picks and smoke test
  • references/export-commands.md: export commands per format

Good fit for

  • A checkpoint has passed promotion and needs deploying
  • You target a modest GPU or a local device

Not for

    Tags

    • export
    • quantization
    • gguf
    • deployment

    About

    You say

    “Export the promoted checkpoint to GGUF with imatrix for a machine with 24 GB of memory.”

    Card for the “Exporting a fine-tuned model to a deployment format” 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 export a fine-tuned model in the format suited to its target
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/export-commands.md12.8 KB
    • SKILL.md8 KB

    Origin and licence

    Listed unmodified

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

    Notice

    « quantized-export » (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.