Hi @Gong1130 🤗
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/2606.06601.
The paper page lets people discuss about your paper and find artifacts linked to it (I see you've already linked your model weights there!). You can also claim the paper as yours which will show up on your public profile at HF.
It's great to see the DIRECT model weights already on the Hub. I noticed in your GitHub README and project page that the release of the curated hybrid dataset (160k pairs) is planned for soon. Would you like to host that dataset on https://huggingface.co/datasets as well?
Hosting on Hugging Face will give the data more visibility and enable better discoverability. It also allows the community to easily use your data with the datasets library:
from datasets import load_dataset
dataset = load_dataset("your-hf-org-or-username/direct-dataset")Besides that, there's the dataset viewer which allows people to quickly explore the first few rows of the data in the browser. Once uploaded, we can also link it directly to the paper page.
Let me know if you're interested or if you need any guidance on the upload process!
Kind regards,
Niels
ML Engineer @ HF 🤗
Hi @Gong1130 🤗
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/2606.06601.
The paper page lets people discuss about your paper and find artifacts linked to it (I see you've already linked your model weights there!). You can also claim the paper as yours which will show up on your public profile at HF.
It's great to see the DIRECT model weights already on the Hub. I noticed in your GitHub README and project page that the release of the curated hybrid dataset (160k pairs) is planned for soon. Would you like to host that dataset on https://huggingface.co/datasets as well?
Hosting on Hugging Face will give the data more visibility and enable better discoverability. It also allows the community to easily use your data with the
datasetslibrary:Besides that, there's the dataset viewer which allows people to quickly explore the first few rows of the data in the browser. Once uploaded, we can also link it directly to the paper page.
Let me know if you're interested or if you need any guidance on the upload process!
Kind regards,
Niels
ML Engineer @ HF 🤗