about the book

 

LLMs in Production is not your typical Data Science book. In fact, you won’t find many books like this at all in the data space mainly because creating a successful data product often requires a large team—data scientists to build models, data engineers to build pipelines, MLOps engineers to build platforms, software engineers to build applications, product managers to go to endless meetings, and, of course, for each of these, managers to take the credit for it all despite their only contribution being to ask questions, oftentimes the same questions repeated, just trying to understand what’s going on.

There are so many books geared toward each of these individuals, but there are so very few that tie the entire process together from end to end. While this book focuses on LLMs—indeed, it can be considered an LLMOps book—what you will take away will be so much more than how to push a large model onto a server. You will gain a roadmap that will show you how to create successful ML products—LLMs or otherwise—that delight end users.

Who should read this book

Anyone who finds themselves working on an application that uses LLMs will benefit from this book. This includes all of the previously listed individuals. The individuals who will benefit the most, though, will likely be those who have cross-functional roles with titles like ML engineer. This book is hands-on, and we expect our readers to know Python and, in particular, PyTorch.

How this book is organized

About the code

liveBook Discussion Forum