Module 1: What are Large Language Models?

Luis Serrano

Luis Serrano

Hello! I'm Luis, your instructor for this module.

Large language models are machine learning models designed to process and analyze text. They are trained on massive amounts of data, and they learn the patterns in the language, allowing them to generate human-like responses to any query we give them.

Large language models are normally based on very large, deep neural networks. Their numerous applications include chatbots, language translation, and text summarization among many others.

In this module, you’ll be learning the architecture of large language models.

To start we will discuss embeddings, which are representations of words and phrases in a high-dimensional space, and how they can be used to measure similarity between different pieces of text.

We will also explore attention, which is a mechanism that allows models to focus on specific parts of the input during processing. We will examine the transformer model architecture, which is the backbone of many state-of-the-art language models, and how it has revolutionized the field of NLP.

Finally, we will delve into semantic search, which is the process of understanding the meaning of a query and finding the most relevant results. We will discuss how large language models can be used to perform semantic search and how this technology is transforming the search industry.

Throughout this module, we will use practical examples and hands-on exercises to ensure that you have a comprehensive understanding of these topics and are able to apply them in real-world scenarios.

I hope you are as excited as I am to learn how large language models work, and how to get the best of them. Let's begin!


What’s Next

Learn about text embeddings, the bread and butter of Large Language Models!