Hi @xuyige 🤗
Niels here from the open-source team at Hugging Face. I discovered your work on Arxiv and was wondering whether you would like to submit it to hf.co/papers to improve its discoverability. If you are one of the authors, you can submit it at https://huggingface.co/papers/submit.
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.
I saw that you've already released the CrossMath evaluation set on the hub here, which is great! It'd be awesome to link it to the paper page once submitted (you just need to add the Arxiv ID to the dataset's metadata).
It'd be great to also make the full 5,000-sample training set and the fine-tuned Qwen3.5-9B checkpoints available on the 🤗 hub, to improve their discoverability/visibility.
Uploading models
See here for a guide: https://huggingface.co/docs/hub/models-uploading.
In this case, since you are using a transformer-based VLM, you could leverage the PyTorchModelHubMixin class or simply upload the LoRA adapters/weights. We encourage researchers to push each model checkpoint to a separate model repository, so that things like download stats also work.
Uploading dataset
Would be awesome to make the training dataset available on 🤗 , so that people can do:
from datasets import load_dataset
dataset = load_dataset("xuyige/CrossMath-train")See here for a guide: https://huggingface.co/docs/datasets/loading.
Let me know if you're interested/need any help regarding this!
Cheers,
Niels
ML Engineer @ HF 🤗
Hi @xuyige 🤗
Niels here from the open-source team at Hugging Face. I discovered your work on Arxiv and was wondering whether you would like to submit it to hf.co/papers to improve its discoverability. If you are one of the authors, you can submit it at https://huggingface.co/papers/submit.
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.
I saw that you've already released the CrossMath evaluation set on the hub here, which is great! It'd be awesome to link it to the paper page once submitted (you just need to add the Arxiv ID to the dataset's metadata).
It'd be great to also make the full 5,000-sample training set and the fine-tuned Qwen3.5-9B checkpoints available on the 🤗 hub, to improve their discoverability/visibility.
Uploading models
See here for a guide: https://huggingface.co/docs/hub/models-uploading.
In this case, since you are using a transformer-based VLM, you could leverage the PyTorchModelHubMixin class or simply upload the LoRA adapters/weights. We encourage researchers to push each model checkpoint to a separate model repository, so that things like download stats also work.
Uploading dataset
Would be awesome to make the training dataset available on 🤗 , so that people can do:
See here for a guide: https://huggingface.co/docs/datasets/loading.
Let me know if you're interested/need any help regarding this!
Cheers,
Niels
ML Engineer @ HF 🤗