Skip to content

Release OmniParser V2 on Hugging Face #223

Description

@NielsRogge

Hi @zhibogogo 🤗

I'm Niels and work as part of the open-source team at Hugging Face. I discovered your work through Hugging Face's daily papers as your latest paper on OmniParser V2 got featured: https://huggingface.co/papers/2502.16161.

The paper page lets people discuss your research and find related artifacts. You can also claim the paper as yours, which will show it on your public HF profile and allow you to link the GitHub and project URLs directly.

I saw in the paper that the code and models are being made available in the AdvancedLiterateMachinery repository. Would you like to host the pre-trained checkpoints for OmniParser V2 on https://huggingface.co/models?

Hosting on Hugging Face will provide significantly more visibility and enable better discoverability through our metadata tagging system (e.g., for image-text-to-text tasks). We can link the models directly to the paper page so that researchers can find and use them instantly.

If you're interested, I've left a guide here. For custom architectures, you can use the PyTorchModelHubMixin class to add from_pretrained and push_to_hub methods, making it very easy for the community to download and run your model.

We would also love to help you build a demo for OmniParser V2 on Spaces. We can provide you with a ZeroGPU grant, which gives you access to A100 GPUs for free to power the demo.

Let me know if you're interested or need any guidance!

Kind regards,

Niels

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions