Build a Large Language Model (From Scratch)

De: Sebastian Raschka

Narrado por: Julie Brierley

Learn how to create, train, and tweak large language models (LLMs) by building one from the ground up!

In Build a Large Language Model (from Scratch) bestselling author Sebastian Raschka guides you step by step through creating your own LLM. Each stage is explained with clear text, diagrams, and examples. You’ll go from the initial design and creation, to pretraining on a general corpus, and on to fine-tuning for specific tasks.

This book teaches you how to:

+ Plan and code all the parts of an LLM

+ Prepare a dataset suitable for LLM training

+ Fine-tune LLMs for text classification and with your own data+ Use human feedback to ensure your LLM follows instructions

+ Load pretrained weights into an LLMBuild a Large Language Model (from Scratch) takes you inside the AI black box to tinker with the internal systems that power generative AI.

As you work through each key stage of LLM creation, you’ll develop an in-depth understanding of how LLMs work, their limitations, and their customization methods. Your LLM can be developed on an ordinary laptop, and used as your own personal assistant.

About the book: This is a practical and eminently-satisfying hands-on journey into the foundations of generative AI. Without relying on any existing LLM libraries, you’ll code a base model, evolve it into a text classifier, and ultimately create a chatbot that can follow your conversational instructions. And you’ll really understand it because you built it yourself!

About the listener: Listeners need intermediate Python skills and some knowledge of machine learning. The LLM you create will run on any modern laptop and can optionally utilize GPUs.

About the author: Sebastian Raschka is a Staff Research Engineer at Lightning AI, where he works on LLM research and develops open-source software.

PLEASE NOTE: When you purchase this title, the accompanying PDF will be available in your Audible Library along with the audio.

©2024 Manning Publications (P)2024 Manning Publications

audio version sucks

no text. pdf hard to find. in fact my pdf seemed to be truncated. I would love to have a complete pdf, without that, it was a waste of money

Really hard to follow when everything is see code

Waste of money. Better to get the pdf and read the book. Every other sentence is see code, see figure etc

Don’t waste your money on the Audible version

The Audible version is a total waste of time and money. It is nearly incomprehensible.

Expensive for the content

I had high hopes to learn a lot. The first chapters are fine to follow with the PDF. The PDF does not contain the book only code and figures. To copy the code you are redirected to an annoying webpage. Listening the book is impossible as the code and result is not narrated. To get the code working you need to copy parts of each chapter following very crossly and understand. I wanted to return this title with my premium plus account but not possible. I closed my audible account after being member since 2O13.

Read by a text to to speech program, not a human. Half the book is references to "see this code".

I really don't know what I was thinking when I decided to get a technical book in audiobook format. I figured it'd at least be read by a human; however, it turns out it was read by an AI. Unfortunately, the quality of the AI narration is far from good.

Next to that: the audiobook format just doesn't make sense for this kind of book. Almost 75% of the book is "see this code": if you're only listening (you don't buy an audiobook to read it with your eyes). So if you were imagining you could learn about building an LLM while doing household chores: that isn't going to work well for you.

Amazon/Audible: if an audiobook is not read by a human: you need to disclose that.

Hard to follow when every other sentence “see code”. Some books don’t convey well in audio

Expressionless voice. Badly edited and hard to follow when involves code inspection. This didn’t work