Release Liquid models on Hugging Face

[NielsRogge]

Hi @wjf5203 🤗

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/2412.04332.
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.

I see in the Github repository that you plan to release several Liquid models, such as Liquid-7B, Liquid-7B-Multiratio and Liquid-7B-IT.
Would be great to host the models you've pre-trained on https://huggingface.co/models once they are available!
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

[wjf5203]

Hi Niels,
Thank you for your kind suggestion! We have already released our model on Hugging Face and launched an online demo. Is there anything else we can do on Hugging Face to further improve this project?
Best,
Junfeng Wu

[NielsRogge]

Great! It seems the model is compatible with the Transformers library, so you can add the library_name as metadata: https://huggingface.co/Junfeng5/Liquid_V1_7B/discussions/1.

In terms of pipeline_tag, it could also be set to image-text-to-text or any-to-any.