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-training LLMs with reinforcement learning using slime v1.0.0

Use this resource to post-train an LLM with reinforcement learning using Megatron-LM and SGLang

New

  • 381 downloads
  • 162 likes
  • 166 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install slime-rl-post-training

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 guides you through installing slime (Docker or source), configuring a source model and launching a GRPO run. It covers custom data generation and integration with Megatron-LM to scale.

Mostly picked by

Updated November 2, 2026

Card for the “Post-training LLMs with reinforcement learning using slime” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: installation, architecture and GRPO training
  • references/api-reference.md and troubleshooting.md: API and troubleshooting

Good fit for

  • You train GLM or Qwen models with reinforcement learning
  • You want custom data generation workflows

Not for

    Tags

    • reinforcement learning
    • megatron
    • grpo
    • llm

    About

    You say

    “Configure a GRPO run with slime on my Qwen model and my generated data.”

    Card for the “Post-training LLMs with reinforcement learning using slime” 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 post-train an LLM with reinforcement learning using Megatron-LM and SGLang
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/api-reference.md12 KB
    • references/troubleshooting.md7.4 KB
    • SKILL.md11.8 KB

    Origin and licence

    Listed unmodified

    Author
    Orchestra Research
    Source
    github.com/orchestra-research/ai-research-skills/tree/773a52944ba4747a18bd4ae9ade53fff041adcbc/06-post-training/slime
    Licence
    MIT

    Notice

    « slime-rl-training » (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.