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.

torchforge: PyTorch-native agentic RL v1.0.0

Use this resource to run SFT or GRPO training with torchforge, keeping algorithms apart from infrastructure

New

  • 536 downloads
  • 205 likes
  • 167 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install torchforge-agentic-rl

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 helps you install torchforge, prepare the PyTorch environment and launch SFT training on two GPUs or GRPO on three. It explains the architecture that separates algorithms from infrastructure. You get launch commands and a base for testing your own algorithms.

Mostly picked by

Updated November 2, 2026

Card for the “torchforge: PyTorch-native agentic RL” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: installation, quick start and architecture
  • references/api-reference.md: API reference
  • references/troubleshooting.md: common issues and fixes

Good fit for

  • You are testing new RL algorithms on several GPUs
  • You want to keep your algorithm code separate from distributed infrastructure

Not for

    Tags

    • torchforge
    • rl
    • pytorch

    About

    You say

    “Launch GRPO training with torchforge on three GPUs for my test model.”

    Card for the “torchforge: PyTorch-native agentic RL” skill

    Skill published by davila7 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 run SFT or GRPO training with torchforge, keeping algorithms apart from infrastructure
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/api-reference.md8.8 KB
    • references/troubleshooting.md7 KB
    • SKILL.md10.9 KB

    Origin and licence

    Listed unmodified

    Author
    davila7
    Source
    github.com/davila7/claude-code-templates/tree/f57964ebda91cdfb31755661ecea9395f30020f1/cli-tool/components/skills/ai-research/post-training-torchforge
    Licence
    MIT

    Notice

    « post-training-torchforge » (davila7, 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.