Optimizing foundation models
Course Overview
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, and the role of agents in multi-step tasks. You will also define methods for fine-tuning an FM, learn how to prepare data for fine-tuning, and more.
Learning objectives
In this course, you will learn how to do the following:
- 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.
- Determine whether an FM effectively meets business objectives.
- Define methods for fine-tuning an FM.
- Describe how to prepare data to fine-tune an FM.
- Determine whether an FM effectively meets the business objectives based on the business metric identified in the use case.
In the next lesson, you will be introduced to a business case for retrieval augmented generation (RAG).