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.

Reinforcement-learning post-training v1.0.0

Use this resource to post-train a large language model with reinforcement learning

New

  • 520 downloads
  • 130 likes
  • 195 saves

Free

Install with the CLI

In a terminal, from the folder you want:

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

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 installs slime, preferably with Docker, configures the source model and runs GRPO training. You get a pipeline that combines Megatron-LM training with SGLang's high-throughput generation.

Mostly picked by

Updated November 2, 2026

Card for the “Reinforcement-learning post-training” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: architecture, installation and a first GRPO run
  • references/: API reference and troubleshooting

Good fit for

  • You train a large model with Megatron-LM
  • You want a custom data-generation flow for RL

Not for

    Tags

    • rl
    • grpo
    • training
    • megatron
    • sglang

    About

    You say

    “Launch a GRPO run on my Qwen3 model with this dataset.”

    Card for the “Reinforcement-learning post-training” 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 a large language model with reinforcement learning
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/api-reference.md11.6 KB
    • references/troubleshooting.md7.1 KB
    • SKILL.md11.2 KB

    Origin and licence

    Listed unmodified

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

    Notice

    « slime » (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.