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.

Configuring LoRA or QLoRA fine-tuning v1.0.0

Use this resource to configure supervised LoRA or QLoRA fine-tuning

New

  • 347 downloads
  • 201 likes
  • 220 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install lora-qlora-training-config

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 writes or reviews the configuration of a LoRA or QLoRA adapter: target modules, rank, alpha, learning rate and effective batch size. It explains when QLoRA buys real headroom and when it mostly adds risk.

Mostly picked by

Updated November 2, 2026

Card for the “Configuring LoRA or QLoRA fine-tuning” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: reference recipe, target modules and Unsloth defaults
  • references/hyperparameters.md: hyperparameters by task
  • references/unsloth-trl-mapping.md: Unsloth and TRL parameter mapping

Good fit for

  • You are writing a LoRA training config for the first time
  • You are choosing between LoRA, QLoRA and full fine-tuning

Not for

    Tags

    • lora
    • qlora
    • hyperparameters
    • fine-tuning

    About

    You say

    “Write the LoRA config for my model on 5,000 support examples.”

    Card for the “Configuring LoRA or QLoRA fine-tuning” 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 configure supervised LoRA or QLoRA fine-tuning
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/hyperparameters.md5.9 KB
    • references/unsloth-trl-mapping.md9.8 KB
    • SKILL.md7.7 KB

    Origin and licence

    Listed unmodified

    Author
    wshobson
    Source
    github.com/wshobson/agents/tree/0874a27b17a22e2b7c2e2bcd725768e0803cad06/plugins/llm-finetuning/skills/lora-qlora-recipes
    Licence
    MIT

    Notice

    « lora-qlora-recipes » (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.