This repo contains code examples of how to create production-grade endpoints for Machine Learning models using the Octo Cloud.
- In the
flan-t5-smalldirectory, you'll find an example of how to containerize a Hugging Face transformers model and deploy that on the OctoAI service. - In the
diffusers-promptherodirectory, you'll find an example of how to containerize a Hugging Face diffusers model and deploy that on the OctoAI service.
A step-by-step explanation of the code and the containerization process can be found in this tutorial in OctoAI's docs.