Frameworks & Templates
From Huggingface Space

From Huggingface Space

You could deploy the gradio application from huggingface space. You could use the full URL of the huggingface space (e.g. (opens in a new tab)) or the space name (e.g. microsoft/HuggingGPT) in the Source field.

Deployment Configuration

After you have successfully deployed your inference deployment, you could visit the detail page to get the endpoint URL:

Deployment Detail

You could use the endpoint URL ( in this case) to use HuggingGPT.


After a idle period, the deployment will be scaled down to 0 replicas. You could visit the detail page to see the current number of replicas. Another request will trigger the deployment to scale up again.