Release SlimSearcher artifacts (models, datasets) on Hugging Face

[NielsRogge]

Hi @zqxie77 🤗

Niels here from the open-source team at Hugging Face. I discovered your work through Hugging Face Paper Pages: https://huggingface.co/papers/2606.07074.

The paper page lets people discuss your paper and find artifacts linked to it (your models or datasets for instance). You can also claim the paper as yours, which will show up on your public profile at HF and allow you to add GitHub and project page URLs.

I saw in your GitHub repository (AntAFu-DeepResearch) that SlimSearcher was recently proposed and is listed as an upcoming resource. It'd be great to make the resulting efficiency-aware search agent checkpoints and the refined search trajectory datasets available on the 🤗 hub once they are ready, to improve their discoverability and visibility within the agentic research community.

We can add metadata 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.

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 leverage the hf_hub_download one-liner to download a checkpoint from the hub.

Uploading datasets

The refined successful trajectories you distilled during SFT would be a very valuable resource for the community. Hosting them on 🤗 allows people to 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 data in the browser.

Let me know if you're interested or need any help regarding this!

Cheers,

Niels
ML Engineer @ HF 🤗