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.

Shrinking and accelerating learning models v1.0.0

Use this resource to reduce a model's size and speed up its inference

New

  • 575 downloads
  • 244 likes
  • 196 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install ml-model-optimization

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 compares compression techniques, plans the ONNX export and measures the accuracy loss at each step. You get a lighter model for an edge device or server, with a quality review.

Mostly picked by

Updated November 2, 2026

Card for the “Shrinking and accelerating learning models” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • SKILL.md: optimization method and the agent's role
  • references/patterns.md: quantization, pruning and export procedures
  • references/sharp_edges.md: accuracy losses and exports that fail on the target

Good fit for

  • Your model is too heavy for a phone or an embedded device
  • Server inference costs too much and must get faster

Not for

    Tags

    • optimization
    • quantization
    • onnx
    • inference
    • model

    About

    You say

    “Quantize my classification model to int8, export it to ONNX and measure the accuracy loss on the test set.”

    Card for the “Shrinking and accelerating learning models” skill

    Skill published by omer-metin under the Apache-2.0 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 reduce a model's size and speed up its inference
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE10.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/patterns.md3.5 KB
    • references/sharp_edges.md5.2 KB
    • references/validations.md2.7 KB
    • SKILL.md1.1 KB

    Origin and licence

    Listed unmodified

    Author
    omer-metin
    Source
    github.com/omer-metin/skills-for-antigravity/tree/e8dcf4e8737921a10088bd5c9eb65e81f74c051f/skills/model-optimization
    Licence
    Apache-2.0

    Notice

    « model-optimization » (omer-metin, Apache-2.0) 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.