Making models available on HF

[NielsRogge]

Hi,

Niels here from the open-source team at Hugging Face. I discovered your work through the paper page: https://huggingface.co/papers/2409.03525 (feel free to claim the paper so that it appears under your HF account!).

I see the checkpoints are currently made available on Google Drive. To improve the discoverability of your work, it would be great to make the models available on the 🤗 hub. We can also add tags to the model cards such as "image-segmentation" so that people can find them when filtering https://huggingface.co/models?pipeline_tag=image-segmentation (although we might need to work on adding a new tag for zero-shot/open vocabulary image segmentation, cc @merveenoyan).

Uploading models

See here for a guide: https://huggingface.co/docs/hub/models-uploading. In this case, we could probably add a from_pretrained method to the main FrozenSeg class here, which leverages the hf_hub_download one-liner to download a checkpoint from the hub.

We encourage researchers to push each model checkpoint to a separate model repository, so that things like download stats also work.

Let me know if you need any help regarding this!

Cheers,

Niels
ML Engineer @ HF 🤗