Hi @giantPanda0906 🤗
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/2511.15848.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models 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 your "Open-source Plan" in the GitHub README (https://github.com/stepfun-ai/Step-Audio-R1) and noticed the checkboxes for "Inference Code", "Online demo", and "Model Checkpoints" are still unchecked. It's fantastic to see your intention to open-source Step-Audio-R1!
We'd be thrilled if you considered making the model checkpoints available on the 🤗 Hub (https://huggingface.co/models) once they are ready. You already have a reserved repository https://huggingface.co/stepfun-ai/Step-Audio-R1 and a Space https://huggingface.co/spaces/stepfun-ai/Step-Audio-R1 which is great! Hosting on Hugging Face will give you more visibility and enable better discoverability for your groundbreaking audio reasoning model. We can help you add pipeline tags like audio-text-to-text to the model card so people can easily find and use it, and link it directly to your paper page.
If you're down, here's a guide for uploading models: https://huggingface.co/docs/hub/models-uploading.
If it's a custom PyTorch model, the PyTorchModelHubMixin class simplifies adding from_pretrained and push_to_hub functionalities.
Once uploaded, we can also link the models to your paper page (read here: https://huggingface.co/docs/hub/en/model-cards#linking-a-paper).
You're also planning an online demo on Spaces – we can even provide you a ZeroGPU grant, which gives you A100 GPUs for free for your demo!
Let me know if you're interested or need any guidance as you prepare for the release!
Kind regards,
Niels
ML Engineer @ HF 🤗
Hi @giantPanda0906 🤗
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/2511.15848.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models 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 your "Open-source Plan" in the GitHub README (https://github.com/stepfun-ai/Step-Audio-R1) and noticed the checkboxes for "Inference Code", "Online demo", and "Model Checkpoints" are still unchecked. It's fantastic to see your intention to open-source Step-Audio-R1!
We'd be thrilled if you considered making the model checkpoints available on the 🤗 Hub (https://huggingface.co/models) once they are ready. You already have a reserved repository
https://huggingface.co/stepfun-ai/Step-Audio-R1and a Spacehttps://huggingface.co/spaces/stepfun-ai/Step-Audio-R1which is great! Hosting on Hugging Face will give you more visibility and enable better discoverability for your groundbreaking audio reasoning model. We can help you add pipeline tags likeaudio-text-to-textto the model card so people can easily find and use it, and link it directly to your paper page.If you're down, here's a guide for uploading models: https://huggingface.co/docs/hub/models-uploading.
If it's a custom PyTorch model, the PyTorchModelHubMixin class simplifies adding
from_pretrainedandpush_to_hubfunctionalities.Once uploaded, we can also link the models to your paper page (read here: https://huggingface.co/docs/hub/en/model-cards#linking-a-paper).
You're also planning an online demo on Spaces – we can even provide you a ZeroGPU grant, which gives you A100 GPUs for free for your demo!
Let me know if you're interested or need any guidance as you prepare for the release!
Kind regards,
Niels
ML Engineer @ HF 🤗