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.

Faster LoRA and QLoRA fine-tuning with Unsloth v1.0.0

Use this resource to speed up LoRA or QLoRA fine-tuning and reduce the GPU memory it needs

New

  • 535 downloads
  • 123 likes
  • 121 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install faster-lora-fine-tuning-unsloth

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 draws on the Unsloth documentation to set up a LoRA or QLoRA fine-tune, reduce memory needs and choose suitable parameters. Unsloth claims training 2 to 5 times faster. You get a lighter training run to launch on your GPU.

Mostly picked by

Updated November 2, 2026

Card for the “Faster LoRA and QLoRA fine-tuning with Unsloth” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: quick reference, common patterns and procedure
  • references/: Unsloth documentation in full and as an index

Good fit for

  • You fine-tune an LLM on a modest graphics card
  • You want to cut the time of a LoRA fine-tune

Not for

    Tags

    • unsloth
    • lora
    • qlora
    • fine-tuning
    • memory

    About

    You say

    “Fine-tune this model with Unsloth in QLoRA and tell me the memory usage.”

    Card for the “Faster LoRA and QLoRA fine-tuning with Unsloth” skill

    Skill published by Orchestra Research 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 speed up LoRA or QLoRA fine-tuning and reduce the GPU memory it needs
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/index.md0.1 KB
    • references/llms-full.md1,052.1 KB
    • references/llms-txt.md794 KB
    • references/llms.md12.2 KB
    • SKILL.md2.2 KB

    Origin and licence

    Listed unmodified

    Author
    Orchestra Research
    Source
    github.com/nousresearch/hermes-agent/tree/0c74cc682dc81bf78b78a1737b3ee77a820ccb79/optional-skills/mlops/training/unsloth
    Licence
    MIT

    Notice

    « unsloth » (Orchestra Research, 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.