This course covers two of the most popular open source platforms for MLOps: MLflow and Hugging Face. We’ll go through the foundations on what it takes to get started in these platforms with basic model and dataset operations. You will start with MLflow using projects and models with its powerful tracking system and you will learn how to interact with these registered models from MLflow with full lifecycle examples.
Class Deals by MOOC List - Click here and see Coursera's Active Discounts, Deals, and Promo Codes.
Then, you will explore Hugging Face repositories so that you can store datasets, models, and create live interactive demos. Through a series of hands-on exercises, learners will gain practical experience working with these open source platforms. By the end of the course, you will be able to apply MLOps concepts like fine-tuning and deploying containerized models to the Cloud. This course is ideal for anyone looking to break into the field of MLOps or for experienced MLOps professionals who want to improve their programming skills.
What You Will Learn
- Create new MLflow projects to create and register models.
- Use Hugging Face models and datasets to build your own APIs.
- Package and deploy Hugging Face to the Cloud using automation.
Syllabus
WEEK 1
Introduction to MLflow
This week, you will learn what MLflow is and how to use it. You’ll install MLflow and perform basic operations like registering runs, models, and artifacts. Then, you’ll create an MLflow project for reproducible results. Finally, you’ll understand how to use a registry with MLflow models and reference artifacts from the API.
WEEK 2
Introduction to Hugging Face
This week, you will learn the basics of the Hugging Face platform. You will use some of its features like its repositories so that you can store models and datasets. Finally, you will learn how to add and use models and datasets using Hugging Face APIs as well as the web interface.
WEEK 3
Deploying Hugging Face
This week, you will learn how to containerize Hugging Face models and use the FastAPI framework to serve the model with an interactive HTTP API endpoint. Once you understand how to put everything together, you’ll use automation for speed and reproducibility. Finally, you’ll use Azure and Docker Hub to store the containers so that they can be used later for deployments.
WEEK 4
Applied Hugging Face
This week, you will learn how to fine-tune Hugging Face models by using pre-existing models and then modifying (fine-tuning) them with additional data. You’ll also use Azure to deploy the container and learn how to troubleshoot it. Finally, you’ll also see how to deploy a model to Hugging Face spaces.
