Release Souped LLM models (SoCE-8B-Ensemble, SoCE-70B-Ensemble) on Hugging Face

Hi @shalini-maiti 🤗

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/2511.13254.
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.

It'd be great to make the souped model checkpoints (SoCE-8B-Ensemble and SoCE-70B-Ensemble) available on the 🤗 hub, to improve their discoverability/visibility.
We can add tags so that people find them when filtering https://huggingface.co/models.

We understand that your repository provides the code to generate these souped models from existing Hugging Face models. It would be fantastic if you could also directly upload the specific pre-computed Souper-Model checkpoints that achieved state-of-the-art results on the Berkeley Function Calling Leaderboard (as mentioned in your paper and README). This would allow users to directly access and use the exact models you evaluated without needing to run the full souping process themselves.

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.

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

Cheers,

Niels
ML Engineer @ HF 🤗