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.

Fine-tuning an LLM with Unsloth on one GPU v1.0.0

Use this resource to fine-tune an LLM on a consumer GPU with Unsloth

New

  • 517 downloads
  • 113 likes
  • 160 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install unsloth-llm-finetuning

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 sizes the run against available VRAM, loads the model, fixes the chat template, attaches LoRA adapters and trains, then picks an export format. It stresses common mistakes: wrong chat template and loss masking. You get a training script and an export for your target runtime.

Mostly picked by

Updated November 2, 2026

Card for the “Fine-tuning an LLM with Unsloth on one GPU” 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: sizing, model loading and chat template
  • SKILL.md: training, export and examples

Good fit for

  • You want to adapt an open model to your domain on a single graphics card
  • You need to export a fine-tuned model in GGUF

Not for

    Tags

    • lora
    • llm
    • gguf

    About

    You say

    “Fine-tune a 7-billion-parameter model on my question-answer pairs, then export it to GGUF.”

    Card for the “Fine-tuning an LLM with Unsloth on one GPU” skill

    Skill published by A-ryanVAT-S 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 fine-tune an LLM on a consumer GPU with Unsloth
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md18.8 KB

    Origin and licence

    Listed unmodified

    Author
    A-ryanVAT-S
    Source
    github.com/sickn33/agentic-awesome-skills/tree/e9809578fd426a284af017c5db99f8eb6628e6ca/skills/unsloth-finetuning
    Licence
    Apache-2.0

    Notice

    « unsloth-finetuning » (A-ryanVAT-S, 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.