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.

Post-train an LLM with TRL v1.0.0

Use this resource to write or fix LLM post-training code with TRL

New

  • 431 downloads
  • 134 likes
  • 132 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-post-training-trl-2

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 picks the trainer that matches the dataset type (SFT, DPO, GRPO, KTO or reward model), sets the useful arguments and fixes dataset format errors. It also covers command-line usage.

Mostly picked by

Updated November 2, 2026

Card for the “Post-train an LLM with TRL” 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: table of trainers and dataset formats
  • SKILL.md: key fields for SFT, GRPO online RL and CLI usage

Good fit for

  • You want to fine-tune a model on your own question-answer pairs
  • A DPO run fails because of your data format

Not for

    Tags

    • TRL
    • LLM
    • training
    • DPO

    About

    You say

    “Write an SFT script with TRL to fine-tune this model on my conversation dataset.”

    Card for the “Post-train an LLM with TRL” skill

    Skill published by huggingface 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 write or fix LLM post-training code with TRL
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md4.3 KB

    Origin and licence

    Listed unmodified

    Author
    huggingface
    Source
    github.com/huggingface/skills/tree/fabc634a893f62ad5c2039830397efa35fa62715/skills/trl-training
    Licence
    Apache-2.0

    Notice

    « trl-training » (huggingface, 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.