Book Image

Pretrain Vision and Large Language Models in Python

By : Emily Webber
4.5 (2)
Book Image

Pretrain Vision and Large Language Models in Python

4.5 (2)
By: Emily Webber

Overview of this book

Foundation models have forever changed machine learning. From BERT to ChatGPT, CLIP to Stable Diffusion, when billions of parameters are combined with large datasets and hundreds to thousands of GPUs, the result is nothing short of record-breaking. The recommendations, advice, and code samples in this book will help you pretrain and fine-tune your own foundation models from scratch on AWS and Amazon SageMaker, while applying them to hundreds of use cases across your organization. With advice from seasoned AWS and machine learning expert Emily Webber, this book helps you learn everything you need to go from project ideation to dataset preparation, training, evaluation, and deployment for large language, vision, and multimodal models. With step-by-step explanations of essential concepts and practical examples, you’ll go from mastering the concept of pretraining to preparing your dataset and model, configuring your environment, training, fine-tuning, evaluating, deploying, and optimizing your foundation models. You will learn how to apply the scaling laws to distributing your model and dataset over multiple GPUs, remove bias, achieve high throughput, and build deployment pipelines. By the end of this book, you’ll be well equipped to embark on your own project to pretrain and fine-tune the foundation models of the future.
Table of Contents (23 chapters)
1
Part 1: Before Pretraining
5
Part 2: Configure Your Environment
9
Part 3: Train Your Model
13
Part 4: Evaluate Your Model
17
Part 5: Deploy Your Model

Detecting bias in ML models

At this point in the book, we’ve covered many of the useful, interesting, and impressive aspects of large vision and language models. Hopefully, some of my passion for this space has started rubbing off on you, and you’re beginning to realize why this is as much of an art as it is a science. Creating cutting-edge ML models takes courage. Risk is inherently part of the process; you hope a given avenue will pay off, but until you’ve followed the track all the way to the end, you can’t be positive. Study helps, as does discussion with experts to try to validate your designs ahead of time, but personal experience ends up being the most successful tool in your toolbelt.

This entire chapter is dedicated to possibly the most significant Achilles heel in ML and artificial intelligence (AI): bias. Notably, here we are most interested in bias toward and against specific groups of human beings. You’ve probably already heard about...