Create an Endpoint

After your first login, you will be directed to the Endpoint creation page. As an example, this guide will go through the steps to deploy distilbert/distilbert-base-uncased-finetuned-sst-2-english for text classification.

1. Enter the Hugging Face Repository ID and your desired Endpoint name

2. Select your Instance Configuration

Choose cloud provider, region, and instance type. If you’re looking for a specific cloud provider, region, or instance that you don’t yet see available, please let us know.

3. Apply Automatic Scale-to-Zero

Or leave your Endpoint as is.

4. Define the Security Level for the Endpoint

5. Customize your Endpoint

Feel free to customize your Endpoint further in Advanced Configuration: replica autoscaling, task, revision, framework, and container type are accessible in this section.

6. Create your Endpoint

By clicking Create Endpoint. The cost estimate displayed is per hour and does not take autoscaling into account.

7. Wait for the Endpoint to build, initialize and run

Note that initializing time depends on the model size and typically takes between 1 to 5 minutes.

8. Test your Endpoint 🎉

This is possible in your Endpoint Overview utilizing Playground 🏁 !

< > Update on GitHub