The data science ecosystem is very competitive at the moment and for entry level candidates, possessing just earning several certificates of completion is no longer enough to earn you that dream job. With the competitive nature of the job market, employers want to see something extra that puts you ahead over others. You might have built a mind-blowing predictive model or a human level conversational chatbot but how can you put your work out there for employers to be able to see, interact with, proving that what they see on your resume is not just hearsay. Most importantly, how do you do this for free? You want something that will always be live and available and will also cost you nothing. This is where this tutorial comes in, providing a quick and easy way to deploy those fancy ML models for prototyping a concept or part of your portfolio projects.

In this tutorial, participants will embark on a hands-on journey to unlock the potential of deploying Machine Learning (ML) models cost-effectively using free cloud infrastructure. The tutorial will focus on two key tools—Streamlit and Hugging Face—showcasing their synergy in creating seamless and interactive ML model deployments. Attendees will be guided through the entire process, from developing a prototype ML model to deploying it on cloud platforms with minimal cost, making it an ideal solution for portfolio showcases or proof-of-concept projects.

Key Components:

Introduction to Streamlit and Hugging Face:

The tutorial will commence with an overview of Streamlit, a powerful Python library for building web applications with minimal effort, and Hugging Face, a platform renowned for its state-of-the-art natural language processing models. Participants will gain a solid understanding of how these tools can be combined for effective ML model deployment.

Building a Prototype ML Model:

Attendees will learn the fundamentals of developing a prototype ML model using popular libraries and frameworks. The focus will be on creating a model that aligns with the tutorial's deployment objectives. Introduction to Free Cloud Infrastructure: The tutorial will provide insights into various cloud platforms offering free tiers suitable for deploying prototype ML models. Participants will learn to navigate these platforms and understand the limitations and advantages of each.

Hands-On Deployment with Streamlit:

Through step-by-step guidance, participants will deploy their prototype ML models using Streamlit, transforming them into interactive web applications. Emphasis will be placed on creating user-friendly interfaces that enhance the model's accessibility.

Utilising Hugging Face for Model Deployment:

Participants will explore Hugging Face's capabilities for model serving and deployment. The tutorial will guide attendees through the process of integrating Hugging Face into the deployment pipeline, showcasing its efficiency in handling diverse ML model types.