Release MTSQL-R1 models and datasets on Hugging Face

[NielsRogge]

Hi @taichengguo 🤗

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/2510.12831.
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 in your abstract and GitHub README that "Full recipes (including code, trained models, logs, reasoning trajectories, etc.) will be released after the internal review" and specifically that you plan to release the MTSQL-R1 (4B) and MTSQL-R1 (1.7B) model checkpoints, as well as the CoSQL-Long-Horizon-SFT-RL-Data and SParC-Long-Horizon-SFT-RL-Data datasets. That's fantastic news!

It'd be great to make these checkpoints and datasets available on the 🤗 hub, to improve their discoverability/visibility once they are officially released.
We can add tags so that people find them when filtering https://huggingface.co/models and https://huggingface.co/datasets.

For your MTSQL-R1 models, the relevant pipeline_tag would likely be table-question-answering.
For your new datasets, the relevant task_category would also be table-question-answering.

Uploading models

See here for a guide: https://huggingface.co/docs/hub/models-uploading.

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 dataset

Would be awesome to make the dataset available on 🤗 , so that people can do:

from datasets import load_dataset

dataset = load_dataset("your-hf-org-or-username/your-dataset")

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, once your internal review is complete!

Cheers,

Niels
ML Engineer @ HF 🤗

[taichengguo]

Thanks for the information! Once the internal review is complete, I will upload the datasets and model to Hugging Face.