Release harvested InternVideo models on Hugging Face

Hi @Revliter 🤗

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/2310.19554.
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, add Github and project page URLs.

I see that the InternVideo project is already very active on Hugging Face with InternVideo2 and InternVideo2.5. Would you like to also host the foundation model checkpoints you've pre-trained using the "harvesting" framework on https://huggingface.co/models?

Hosting on Hugging Face will give these specific models more visibility and enable better discoverability within the community. We can add metadata tags to the model cards so that people find them easier when filtering for video-language tasks, and link them directly to the paper page.

If you're down, I'm leaving a guide here. If they are custom models, you can use the PyTorchModelHubMixin class which adds from_pretrained and push_to_hub functionality, or simply use hf_hub_download for easy checkpoint access.

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

Let me know if you're interested or need any guidance!

Kind regards,

Niels

Start with the linked Hugging Face model-uploading guide and identify the harvested foundation-model checkpoints referenced by the issue. Done means the checkpoints are hosted on Hugging Face with discoverability metadata and linked to the paper page; the issue provides no repository files or tests to run.