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.

Fine-tuning OpenVLA-OFT for robot control v1.0.0

Use this resource to fine-tune and evaluate OpenVLA-OFT policies that generate robot actions

New

  • 533 downloads
  • 124 likes
  • 195 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install openvla-oft-robot-finetuning

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 the openvla-oft repository, evaluating a checkpoint on LIBERO, then fine-tuning the model with LoRA on your data. It also covers client-server deployment for ALOHA and normalization pitfalls.

Mostly picked by

Updated November 2, 2026

Card for the “Fine-tuning OpenVLA-OFT for robot control” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: installation, evaluation and training workflows
  • references/aloha-workflow.md, libero-workflow.md, config-troubleshooting.md and paper-and-checkpoints.md: ALOHA, LIBERO, troubleshooting and checkpoints

Good fit for

  • You want to reproduce OpenVLA-OFT results
  • You train a custom action head for a robot

Not for

    Tags

    • robotics
    • vla
    • lora
    • evaluation

    About

    You say

    “Evaluate the OpenVLA-OFT LIBERO checkpoint, then fine-tune it on my demonstrations.”

    Card for the “Fine-tuning OpenVLA-OFT for robot control” 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 fine-tune and evaluate OpenVLA-OFT policies that generate robot actions
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/aloha-workflow.md3.9 KB
    • references/config-troubleshooting.md4 KB
    • references/libero-workflow.md3.1 KB
    • references/paper-and-checkpoints.md2.6 KB
    • SKILL.md14.9 KB

    Origin and licence

    Listed unmodified

    Author
    Orchestra Research
    Source
    github.com/orchestra-research/ai-research-skills/tree/773a52944ba4747a18bd4ae9ade53fff041adcbc/18-multimodal/openvla-oft
    Licence
    MIT

    Notice

    « fine-tuning-openvla-oft » (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.