Release StreamingVLM model and link datasets on Hugging Face #2
Description
Hi @Guangxuan-Xiao 🤗
Niels here from 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/2510.09608.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models, datasets or demo 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.
It'd be great to make the StreamingVLM checkpoints and the Inf-Stream-Train and Inf-Stream-Eval datasets even more discoverable/visible on the 🤗 hub.
We can add tags so that people find them when filtering https://huggingface.co/models and https://huggingface.co/datasets.
Uploading models
See here for a guide: https://huggingface.co/docs/hub/models-uploading.
It seems the pre-trained StreamingVLM model checkpoint is not yet explicitly available for download on a public platform. It would be awesome if you could upload the pre-trained weights for StreamingVLM to the Hugging Face Hub!
In this case, we could leverage the PyTorchModelHubMixin class which adds from_pretrained and push_to_hub to any custom nn.Module. Alternatively, one can 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. We can then also link the checkpoints to the paper page.
Uploading/Linking datasets
It appears the Inf-Stream-Train and Inf-Stream-Eval datasets might already be on the Hugging Face Hub under mit-han-lab/. If so, that's fantastic! It would be great to ensure they are officially linked to your paper page and have rich metadata so people can easily do:
from datasets import load_dataset
dataset = load_dataset("mit-han-lab/Inf-Stream-Train")
# or
dataset = load_dataset("mit-han-lab/Inf-Stream-Eval")See here for a guide: https://huggingface.co/docs/datasets/loading.
Besides that, there's the dataset viewer which allows people to quickly explore the first few rows of the data in the browser.
Let me know if you're interested/need any help regarding this!
Cheers,
Niels
ML Engineer @ HF 🤗