From the course: MLOps Tools: MLflow and Hugging Face

Unlock this course with a free trial

Join today to access over 24,900 courses taught by industry experts.

Using GitHub Actions for model deployments

Using GitHub Actions for model deployments - Hugging Face Tutorial

From the course: MLOps Tools: MLflow and Hugging Face

Start my 1-month free trial Buy for my team

Using GitHub Actions for model deployments

“

- Let's go through some of the things that you'll have to know and understand in order to be able to use GitHub actions for model deployments and specifically Huggingface. So we're going to take a look and we're going to be working with this repository called "Huggingface Deploy Azure." And what we're going to be doing here is go through some of the details that are required and then we'll take several different approaches to actually deploy. So the first thing that I want to show you is that this is a web application similar to what we've seen before in, in many of the examples is going to be using GPT-2 for doing some text generation live through the FastAPI that is being exposed. So there's nothing much to it. Let's take a look, a quick look at the, the dependencies and then the docker file and then we'll go through some of the more interesting parts on the GitHub action side of things. So Transformers, let's see TensorFlow FastAPI and Uvicorn so that we are able to run these. So…

Contents