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.

RLHF training at scale with OpenRLHF v1.0.0

Use this resource to train large models with RLHF methods such as PPO, GRPO or DPO using OpenRLHF

New

  • 320 downloads
  • 241 likes
  • 192 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install openrlhf-rlhf-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 helps you install OpenRLHF, chain an SFT, reward-model and PPO pipeline, or launch GRPO or DPO training without a critic model. It also explains how to scale to multiple nodes. You get training commands ready to adapt.

Mostly picked by

Updated November 2, 2026

Card for the “RLHF training at scale with OpenRLHF” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: installation, commands and PPO, GRPO and DPO workflows
  • references/multi-node-training.md: training across several nodes
  • references/custom-rewards.md: custom reward functions

Good fit for

  • You are aligning a 7B to 70B+ model on preferences
  • You want to compare PPO, GRPO and DPO on your dataset

Not for

    Tags

    • rlhf
    • llm
    • training

    About

    You say

    “Set up a DPO pipeline to align my 7B Qwen model on my preference pairs.”

    Card for the “RLHF training at scale with OpenRLHF” 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 train large models with RLHF methods such as PPO, GRPO or DPO using OpenRLHF
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/algorithm-comparison.md9.9 KB
    • references/custom-rewards.md16 KB
    • references/hybrid-engine.md7.4 KB
    • references/multi-node-training.md11.3 KB
    • SKILL.md8.4 KB

    Origin and licence

    Listed unmodified

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

    Notice

    « post-training-openrlhf » (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.