Build a Large Language Model (From Scratch) is now in print!
Save half with code PLRASCHKA50
Is this your brand on Milled? Claim it.
An instant classic! Sebastian Raschka’s Build a Large Language Model (From Scratch) is now available in print and ready to start shipping today! Order now, and you can start reading immediately. Every Manning print book comes with instant access to the eBook versions.
Build a Large Language Model (From Scratch) is a practical and eminently-satisfying hands-on journey into the foundations of generative AI. In this one-of-a-kind book, you’ll code a base model, evolve it into a text classifier, and ultimately create a chatbot that can follow your conversational instructions without relying on any existing LLM libraries. And you’ll really understand it because you built it yourself!
eBook $47.99$23.99 Print + eBook $59.99$29.99
liveAudio + liveBook $49.99$24.99
SAVE HALF on Build a Large Language Model (From Scratch) and other
selected books!
Use code PLRASCHKA50 at checkout.
This offer expires midnight PT, October 3. Only at manning.com.
Chapter 1: Get a crystal clear introduction to LLMs, including the transformer architecture. Start reading chapter 1 now in liveBook!
Chapter 2: Start building your first LLM by preparing text for LLM training, including splitting text into tokens, using byte pair encoding, the sliding window approach, and converting tokens into vectors.
Chapter 3: Dive into attention with a basic self-attention framework. You’ll also create a causal attention module to generate one token at a time, mask attention weights with dropout to reduce overfitting, and stacki multiple causal attention modules into a multihead attention module.
Chapter 4: Code a GPT-like LLM that can be trained to generate human-like text. You’ll learn about normalizing layer activations, shortcut connections to train models more effectively, transformer blocks to create GPT models of various sizes, and computing the number of parameters and storage requirements of GPT models.
The book’s clear figures and diagrams make complex concepts easy to understand.
Chapter 5: All about pretraining, including assessing the quality of LLM-generated text, saving and loading model weights, and loading pretrained weights from OpenAI.
Chapter 6: Finetune your LLM by preparing a dataset for text classification, modifying your pretrained LLM to identify spam messages, and evaluating the accuracy of your fine-tuned classifier.
Chapter 7: Learn about instruction fine-tuning by preparing a dataset for supervised instruction fine-tuning, organizing instruction data in training batches, loading a pretrained LLM and fine-tuning it to follow human instructions.
Sebastian Raschka, PhD has been working in machine learning and AI for more than a decade. In addition to being a researcher, Sebastian has a strong passion for education. He is known for his bestselling books on machine learning with Python and his contributions to open source. Sebastian is a staff research engineer at Lightning AI, focusing on implementing and training LLMs. Before his industry experience, Sebastian was an assistant professor in the Department of Statistics at the University of Wisconsin-Madison, where he focused on deep learning research.
You don’t need a supercomputer to build your own LLM! All code examples in the book have been carefully designed to run efficiently on a regular laptop without any special hardware. If you have access to a GPU, you'll find helpful tips on scaling up the datasets and models to take advantage of that extra power.
You don’t need to be an AI expert to build a large language model from scratch—all you need is intermediate Python skills and some knowledge of machine learning. If you want to get started, Sebastian Raschka offers several free courses on his website to help you quickly get up to speed with everything you need to know about the latest techniques.
You can use code PLRASCHKA50 to SAVE HALF on these Manning books, as well!
In clear, plain language, this illuminating book shows you when and why LLMs make errors, and how you can account for inaccuracies in your AI solutions. Once you know how LLMs work, you’ll be ready to start exploring the bigger questions of AI, such as how LLMs “think” differently that humans, how to best design LLM-powered systems that work well with human operators, and what ethical, legal, and security issues can—and will—arise from AI automation. [Read more]
7 chapters of this MEAP are available now, with more to follow soon!
eBook $39.99$19.99 Print + eBook $49.99$24.99
Included with your Manning Online Pro subscription! [learn more]
Learn Generative AI with PyTorch
Learn the underlying mechanics of generative AI by building working AI models from scratch. Every model you’ll create is fun and fascinating, in projects that include generating color images of anime faces, changing the hair color in a photograph, training a model to write like Hemingway, and generating music in the style of Mozart. [Read more]
All chapters of this MEAP are available now!
eBook $47.99$23.99 Print + eBook $59.99$29.99
Included with your Manning Online Pro subscription! [learn more]
Hugging Face is the ultimate resource for machine learning engineers and AI developers. It provides hundreds of pretrained and open-source models for dozens of different domains—from natural language processing to computer vision. Plus, you’ll find a popular platform for hosting your models and datasets. [Read more]
3 chapters of this MEAP are available now, with more to follow soon!
eBook $39.99$19.99 Print + eBook $49.99$24.99
Included with your Manning Online Pro subscription! [learn more]
Multi-Agent Systems with AutoGen
Get familiar with building multi-agent applications and AutoGen, an open source AI framework to create AI assistants that can handle tasks once impossible to automate. You’ll apply the techniques you learn to building a whole host of useful AI assistants—from AI financial analysts capable of analyzing stocks, to travel agents that can search and book flights to your budget and preferences. [Read more]
2 chapters of this MEAP are available now, with more to follow soon!
eBook $47.99$23.99 Print + eBook $59.99$29.99
Included with your Manning Online Pro subscription! [learn more]
A Simple Guide to Retrieval Augmented Generation
Generative AI models struggle when you ask them about facts not covered in their training data. Retrieval Augmented Generation—or RAG—enhances an LLM’s available data by adding context from an external knowledge base, so it can answer accurately about proprietary content, recent information, and even live conversations. RAG is powerful, and with this book, it’s also easy to understand and implement! [Read more]
5 chapters of this MEAP are available now, with more to follow soon!
eBook $39.99$19.99 Print + eBook $49.99$24.99
Included with your Manning Online Pro subscription! [learn more]
