Release CCF models on Hugging Face #1
Description
Hi @ 🤗
I'm Niels and work as part of the open-source team at Hugging Face. I discovered your work on CCF for domain generalized multi-modal 3D object detection through Hugging Face's daily papers: https://huggingface.co/papers/2603.23276.
I saw in your paper that you plan to release the code and models at https://github.com/IMPL-Lab/CCF. Since the repository doesn't seem to be accessible yet, I wanted to reach out and suggest hosting your pre-trained model checkpoints on Hugging Face!
Hosting on Hugging Face will give your work significantly more visibility and enable better discoverability. We can add metadata tags to the model cards so that researchers can find your work easier when filtering for tasks like 3D object detection.
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 methods to your model, allowing people to download and use your checkpoints with a single line of code.
Once uploaded, we can link the models directly to the paper page (see here) so the community can easily discover them.
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 or need any guidance!
Kind regards,
Niels
ML Engineer @ HF 🤗