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.

YAML-driven LLM fine-tuning v1.0.0

Use this resource to fine-tune an LLM with a YAML configuration, using LoRA, QLoRA or preference methods

New

  • 422 downloads
  • 140 likes
  • 231 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install yaml-llm-fine-tuning-axolotl

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 the training YAML configuration, picks the dataset format and method, then runs the fine-tune. You get a reproducible fine-tune described in a single file.

Mostly picked by

Updated November 2, 2026

Card for the “YAML-driven LLM 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: overview, configuration templates and use cases
  • references/: API, dataset formats and other references

Good fit for

  • You want a reproducible training run described in a file
  • You are comparing LoRA with a preference-alignment method

Not for

    Tags

    • axolotl
    • yaml
    • fine-tuning
    • lora
    • alignment

    About

    You say

    “Write the YAML configuration to fine-tune this model with QLoRA on my dataset.”

    Card for the “YAML-driven LLM fine-tuning” 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 fine-tune an LLM with a YAML configuration, using LoRA, QLoRA or preference methods
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/api.md118.3 KB
    • references/dataset-formats.md45 KB
    • references/index.md0.2 KB
    • references/other.md137.1 KB
    • SKILL.md4.8 KB

    Origin and licence

    Listed unmodified

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

    Notice

    « axolotl » (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.