Create Dedicated Endpoint from Lepton Photon

You can create a dedicated endpoint from the photons you have built by selecting the Create from Lepton Photon option.

For example, we assume that you have a gpt2-photon pushed to your workspace, which is the HuggingFace implementation of the GPT-2 model, suitable to be run on a small CPU server.

Select the photon in the creation page, and you can create a dedicated endpoint from your gpt2-photon photon with your desired configurations.

For more details about photons, please refer to The Anatomy of a Photon. For information about configuration options, see the Configuration Options.