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.

Adapt a pretrained model: prompt, RAG or LoRA v1.0.0

Use this resource to adapt a pretrained model to a domain, a style or a task

New

  • 472 downloads
  • 107 likes
  • 185 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install ml-fine-tuning-adaptation

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 adaptation methods, prepares the dataset, sets up QLoRA with PEFT and training with TRL. You get a justified method and a training script.

Mostly picked by

Updated November 2, 2026

Card for the “Adapt a pretrained model: prompt, RAG or LoRA” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: method selection table and dataset preparation
  • SKILL.md: QLoRA and PEFT setup, then TRL training

Good fit for

  • You want to adapt a model to a customer-service tone with LoRA
  • You must decide whether RAG is enough before training

Not for

    Tags

    • fine-tuning
    • lora
    • qlora
    • peft
    • dataset

    About

    You say

    “Help me adapt an open-source model to our customer-service tone with LoRA.”

    Card for the “Adapt a pretrained model: prompt, RAG or LoRA” skill

    Skill published by josiahsiegel 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 adapt a pretrained model to a domain, a style or a task
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md8.1 KB

    Origin and licence

    Listed unmodified

    Author
    josiahsiegel
    Source
    github.com/josiahsiegel/claude-plugin-marketplace/tree/5a1b1123b9e50aa9a66a61005ca6fe012cc7442d/plugins/ml-master/skills/ml-fine-tuning
    Licence
    MIT

    Notice

    « ml-fine-tuning » (josiahsiegel, 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.