Hi @Mingyuan1997 馃
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/2505.19255.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models for instance), and you can also claim the paper as yours which will show up on your public profile at HF, and add GitHub and project page URLs.
I noticed in your GitHub README that the model checkpoints for VTool-R1 (3B, 7B, and 32B) are "Coming Soon" and that you have placeholders for Hugging Face links. We would love to help you host these on the Hub!
Would you like to host the models you've trained on https://huggingface.co/models?
Hosting on Hugging Face will give your work more visibility and enable better discoverability. We can add tags in the model cards so that people find the models easier, link them to the paper page, etc.
If you're down, leaving a guide here. Since these appear to be based on Qwen2.5-VL, you can likely use the push_to_hub methods from the Transformers library or use the hf_hub_download utility.
We would also be happy to help you host the preprocessed datasets you've shared on Google Drive on https://huggingface.co/datasets as well, which would allow people to load them easily with:
from datasets import load_dataset
dataset = load_dataset("VTool-R1/ReFocus-Preprocessed")After uploaded, we can link everything to the paper page so people can discover your work easily.
Let me know if you're interested or need any guidance!
Kind regards,
Niels
Hi @Mingyuan1997 馃
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/2505.19255.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models for instance), and you can also claim the paper as yours which will show up on your public profile at HF, and add GitHub and project page URLs.
I noticed in your GitHub README that the model checkpoints for VTool-R1 (3B, 7B, and 32B) are "Coming Soon" and that you have placeholders for Hugging Face links. We would love to help you host these on the Hub!
Would you like to host the models you've trained on https://huggingface.co/models?
Hosting on Hugging Face will give your work more visibility and enable better discoverability. We can add tags in the model cards so that people find the models easier, link them to the paper page, etc.
If you're down, leaving a guide here. Since these appear to be based on Qwen2.5-VL, you can likely use the
push_to_hubmethods from the Transformers library or use the hf_hub_download utility.We would also be happy to help you host the preprocessed datasets you've shared on Google Drive on https://huggingface.co/datasets as well, which would allow people to load them easily with:
After uploaded, we can link everything to the paper page so people can discover your work easily.
Let me know if you're interested or need any guidance!
Kind regards,
Niels