Generative AI: Working with Large Language Models

1h 22mAdvanced2025-03-17

Authors

Jonathan Fernandes

Consultant focusing on data science, AI, and big data

Course details

Transformers have quickly become the go-to architecture for natural language processing (NLP). As a result, knowing how to use them is now a business-critical skill in your AI toolbox. In this course, instructor Jonathan Fernandes walks you through many of the key large language models developed since GPT-3. He presents a high-level overview of GLaM, Megatron-Turing NLG, Gopher, Chinchilla, PaLM, OPT, and BLOOM, relaying some of the most important insights from each model.

Get a high-level overview of large language models, where and how they are used in production, and why they are so important to NLP. Additionally, discover the basics of transfer learning and transformer training to optimize your AI models as you go. By the end of this course, you’ll be up to speed with what’s happened since OpenAI first released GPT-3 as well as the key contributions of each of these large language models.

Skills covered

Natural Language Processing (NLP)AdvancedGenerative AIArtificial Intelligence (AI)

Concepts

0. Introduction

01 - Learning about Large Language Models

1. Transformers in NLP

02 - What are large language models
03 - Transformers in production
04 - Transformers - History

2. Training Transformers and Their Architecture

05 - Transfer learning
06 - Transformer - Architecture overview
07 - Self-attention
08 - Multi-head attention and Feed Forward Network

3. Large Language Models

09 - GPT-3
10 - GPT-3 use cases
11 - Challenges and shortcomings of GPT-3
12 - GLaM
13 - Megatron-Turing NLG Model
14 - Gopher
15 - Scaling laws
16 - Chinchilla
17 - BIG-bench
18 - PaLM
19 - OPT and BLOOM
20 - GitHub models
21 - Accessing Large Language Models using an API
22 - Inference time vs. pre-training

Conclusion

23 - Going further with Transformers