Optimizing Foundation Models

About this course

In this course, you will explore two techniques to improve the performance of a foundation model (FM): Retrieval Augmented Generation (RAG) and fine-tuning. You will learn about Amazon Web Services (AWS) services that help store embeddings with vector databases, the role of agents in multi-step tasks, define methods for fine-tuning an FM, how to prepare data for fine-tuning, and more.

What you will learn

• Identify AWS services that help store embeddings with vector databases.
• Understand the role of agents in multi-step tasks.
• Understand approaches to evaluate FM performance and determine whether an FM effectively meets business objectives.