Skip to content

Release Rotation Trick Model Checkpoints on Hugging Face #3

@NielsRogge

Description

@NielsRogge

Hi @cfifty 🤗

I'm Niels from the Hugging Face open-source team. I came across your ICLR 2025 paper, "Restructuring Vector Quantization with the Rotation Trick," via our daily papers feature: https://huggingface.co/papers/2410.06424. Your work on improving VQ-VAEs is very interesting!

I noticed you've released pretrained model checkpoints on Google Drive. To maximize their discoverability and impact, we'd love to see them hosted on the Hugging Face Hub. This would provide:

  • Increased visibility: Researchers can easily find and use your models.
  • Improved discoverability: We can add relevant tags to the model cards, making it easier for others to find them based on their use case.
  • Integration with the Hugging Face ecosystem: Seamless integration with other tools and datasets on the Hub.

We have detailed guides for uploading models to the Hub: Model Uploading Guide. For PyTorch models, the PyTorchModelHubMixin simplifies the process: PyTorchModelHubMixin.

Would you be open to migrating your checkpoints to Hugging Face? Let me know if you have any questions or need assistance.

Best regards,

Niels
ML Engineer @ Hugging Face 🤗

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions