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.

Compressing LLMs with knowledge distillation v1.0.0

Use this resource to compress a large language model into a smaller one

New

  • 383 downloads
  • 128 likes
  • 136 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-knowledge-distillation

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 sets up distillation from a teacher model to a student model: distillation loss, training loop and the MiniLLM variant with reverse KL divergence. You get the training code and the settings to check.

Mostly picked by

Updated November 2, 2026

Card for the “Compressing LLMs with knowledge distillation” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: loading both models, distillation loss and training loop
  • references/minillm.md: the MiniLLM variant with reverse KL divergence

Good fit for

  • You want a smaller model that keeps good performance
  • You want to cut the inference cost of a hosted model

Not for

    Tags

    • distillation
    • llm
    • compression
    • training

    About

    You say

    “Distill my large model into a smaller one to reduce inference costs.”

    Card for the “Compressing LLMs with knowledge distillation” skill

    Skill published by davila7 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 compress a large language model into a smaller one
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.6 KB
    • references/minillm.md9.2 KB
    • SKILL.md13.8 KB

    Origin and licence

    Listed unmodified

    Author
    davila7
    Source
    github.com/davila7/claude-code-templates/tree/f57964ebda91cdfb31755661ecea9395f30020f1/cli-tool/components/skills/ai-research/emerging-techniques-knowledge-distillation
    Licence
    MIT

    Notice

    « emerging-techniques-knowledge-distillation » (davila7, 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.