Release RQ-VAE Recommender checkpoints on Hugging Face

[NielsRogge]

Hello @EdoardoBotta 🤗

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 yours got featured: https://huggingface.co/papers/2305.05065.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models for instance),
you can also claim the paper as yours which will show up on your public profile at HF.

Would you like to host the RQ-VAE tokenizer model and the retrieval model you've pre-trained on https://huggingface.co/models?
Hosting on Hugging Face will give you more visibility/enable better discoverability. We can add tags in the model cards so that people find the models easier,
link it to the paper page, etc.

If you're down, leaving a guide here. If it's a custom PyTorch model, you can use the PyTorchModelHubMixin
class which adds from_pretrained and push_to_hub to the model which lets you to upload the model and people to download and use models right away.
If you do not want this and directly want to upload model through UI or however you want, people can also use hf_hub_download.

After uploaded, we can also link the models to the paper page (read here) so people can discover your model.

You can also build a demo for your model on Spaces, we can provide you a ZeroGPU grant,
which gives you A100 GPUs for free.

Let me know if you're interested/need any guidance :)

Kind regards,

Niels

[EdoardoBotta]

Hi @NielsRogge ,

thank you for reaching out and the detailed guide, I was not familiar with this process. I have used the PyTorchModelHubMixin to upload the model checkpoint and create the model page.

Can you confirm the model page is correctly set up and the model is linked to the original paper?

[NielsRogge]

Oh that's awesome :) the model card looks great. Thanks to the use of the Mixin class, downloads will also work (they are incremented each time someone runs the from_pretrained method).