This course is divided into two parts. First, we will focus on Build, Train, and Deploy Models with AWS SageMaker (Part 1). After completing Part 1, we will move on to Fine-Tuning LLMs with QLoRA, AWS, and Open Source (Part 2).

The lessons are organized into separate sections. One section is marked “From here we start Part 1,” where we cover building, training, and deploying models using AWS SageMaker. Another section is marked “From here we start Part 2,” where we focus on fine-tuning large language models using QLoRA, AWS, and open-source tools.