Demo for this model on Spaces
Hi @netease-youdao 🤗
I'm Apolinario, from the open-source team at Hugging Face. Congrats and thanks for open-sourcing netease-youdao/Confucius4-R2T2 on the Hub! We were excited about this work and built with an agent an interactive demo app of it on Hugging Face Spaces, running on a free ZeroGPU infrastructure.
Here's a link to the demo: https://huggingface.co/spaces/hugging-apps/confucius4-r2t2-demo
We would love to transfer this demo to you or your organization. Would you like this demo to live under your own account or organization? If so just let me know here which username to transfer to, and we'll transfer the Space over to you, we hope it can give your work more visibility, discoverability and allows folks to try it out.
(If you have any questions or just want to chat more about this, you can find me on Twitter, LinkedIn or apolinario @ huggingface.co)
Cheers,
Poli
Hi Poli! 🤗
Thanks a lot for reaching out, and especially for building this demo for Confucius4-R2T2 — we really appreciate the support from the Hugging Face team!
The Space looks great, and we'd be very happy to have it transferred to our Hugging Face organization: netease-youdao.
One small note: we noticed that the current demo may run into issues with longer audio clips, since the default inference budget appears to be limited to 512 tokens, which may cause longer transcriptions to be truncated. We can take a closer look and adjust the inference settings once the Space is transferred.
Also, could you confirm whether the Space will retain its current ZeroGPU setup after the transfer, including the current GPU allocation, and whether there are any hosting costs or organization-level quota requirements on our side?
Thanks again for helping make R2T2 more accessible and easier for people to try out!
Cheers,
The Confucius4-R2T2 Team
Also, could you confirm whether the Space will retain its current ZeroGPU setup after the transfer, including the current GPU allocation, and whether there are any hosting costs or organization-level quota requirements on our side?
Yes, we'll provide ZeroGPU to the Space as a grant, no hosting costs or org quota required. Cheers!