TomShine - 标记
Build a Large Language Model Goodreads 豆瓣
作者: Sebastian Raschka Manning 2025 - 4 其它标题: Build a Large Language Model (From Scratch)
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), you’ll discover how LLMs work from the inside out. In this insightful book, bestselling author Sebastian Raschka guides you step by step through creating your own LLM, explaining each stage with clear text, diagrams, and examples. You’ll go from the initial design and creation to pretraining on a general corpus, all the way to finetuning for specific tasks.

Build a Large Language Model (from Scratch) teaches you how to:

- Plan and code all the parts of an LLM
- Prepare a dataset suitable for LLM training
- Finetune LLMs for text classification and with your own data
- Use human feedback to ensure your LLM follows instructions
- Load pretrained weights into an LLM

The large language models (LLMs) that power cutting-edge AI tools like ChatGPT, Bard, and Copilot seem like a miracle, but they’re not magic. This book demystifies LLMs by helping you build your own from scratch. You’ll get a unique and valuable insight into how LLMs work, learn how to evaluate their quality, and pick up concrete techniques to finetune and improve them.

The process you use to train and develop your own small-but-functional model in this book follows the same steps used to deliver huge-scale foundation models like GPT-4. Your small-scale LLM can be developed on an ordinary laptop, and you’ll be able to use it as your own personal assistant.
about the book

Build a Large Language Model (from Scratch) is a one-of-a-kind guide to building your own working LLM. In it, machine learning expert and author Sebastian Raschka reveals how LLMs work under the hood, tearing the lid off the Generative AI black box. The book is filled with practical insights into constructing LLMs, including building a data loading pipeline, assembling their internal building blocks, and finetuning techniques. As you go, you’ll gradually turn your base model into a text classifier tool, and a chatbot that follows your conversational instructions.
2025年3月4日 已读
Atomic Habits: An Easy & Proven Way to Build Good Habits & Break Bad Ones Goodreads
Atomic Habits: An Easy & Proven Way to Build Good Habits & Break Bad Ones
8.6 (11 个评分) 作者: James Clear 译者: Gunnar Nyquist / Nagalakshmi Shanmugam Avery 2018 - 10
No matter your goals,
offers a proven framework for improving--every day. James Clear, one of the world's leading experts on habit formation, reveals practical strategies that will teach you exactly how to form good habits, break bad ones, and master the tiny behaviors that lead to remarkable results.
If you're having trouble changing your habits, the problem isn't you. The problem is your system. Bad habits repeat themselves again and again not because you don't want to change, but because you have the wrong system for change. You do not rise to the level of your goals. You fall to the level of your systems. Here, you'll get a proven system that can take you to new heights.
Clear is known for his ability to distill complex topics into simple behaviors that can be easily applied to daily life and work. Here, he draws on the most proven ideas from biology, psychology, and neuroscience to create an easy-to-understand guide for making good habits inevitable and bad habits impossible. Along the way, readers will be inspired and entertained with true stories from Olympic gold medalists, award-winning artists, business leaders, life-saving physicians, and star comedians who have used the science of small habits to master their craft and vault to the top of their field.
Learn how to:
make time for new habits (even when life gets crazy);
overcome a lack of motivation and willpower;
design your environment to make success easier;
get back on track when you fall off course;
...and much more.
will reshape the way you think about progress and success, and give you the tools and strategies you need to transform your habits--whether you are a team looking to win a championship, an organization hoping to redefine an industry, or simply an individual who wishes to quit smoking, lose weight, reduce stress, or achieve any other goal.
2025年3月4日 已读
C++新经典 豆瓣
作者: 王健伟 清华大学出版社 2020 - 8
本书是一部C/C++编程语言书,定位在C/C++语言本身的讲解上面。本书包含纸质图书以及教学源代码文件。
本书共分为三部分:第1部分为C/C++语言概述(第1章),主要介绍了C和C++语言的起源、市场需求、就业形势及如何搭建语言开发环境等内容。第2部分为C语言(第2~12章),主要介绍C语言的各种开发知识,包括基础知识,如常量、变量、表达式、程序结构、数组、函数等,也包括高级知识,如指针、结构、位运算、文件等,本部分的学习正是为后面的学习打下基础。第3部分C++语言(第13~20章),主要介绍C++语言的各种开发知识,包括基础知识比如面向对象编程、命名空间、容器、迭代器,也包括类的详细介绍、模板与泛型的详细介绍;高级知识比如智能指针详细介绍、并发与多线程详细介绍;扩展知识比如内存高级话题、STL标准模板库大局观,C++11新标准比如可调用对象、万能引用、函数模板类型推断、引用折叠、完美转发、auto推断、decltype、lambda表达式、初始化列表、类型萃取等。
本书以择业为导向,涵盖90%的C/C++语言常用开发知识,通俗易懂、范例众多,对于希望从事C/C++开发的读者极具实用价值,本书是一本不可多得的、值得珍藏并能够陪伴读者数年甚至数十年的参考书。
本书主要适合以下几类读者:
(1)C/C++语言初学者或者其他计算机语言转到C/C++语言的程序员。
(2)从事C/C++开发多年的程序员,希望能够详细地复习一下基础的C/C++知识,把整个知识线串一串,形成一个比较完整的学习体系。
(3)已经掌握C++98标准,但是需要进一步学习C++11/14/17新标准的程序员。
2025年2月21日 已读
对自己来说有些简单,有些地方
C++ 软件开发
搞定系统设计:面试敲开大厂的门 豆瓣
作者: Alex Xu 译者: 徐江 电子工业出版社 2023 - 11
系统设计面试被认为是所有技术面试中难度最大的面试,因为面试题的范围都非常广且模糊,其答案也是开放的,不存在标准答案或正确答案。本书是专门为准备系统设计面试的读者而撰写的,重点讨论了分布式系统中的常用组件和大型Web 应用的系统架构,涵盖了几类常见的典型应用,包括聊天系统、视频流系统、文件存储系统(云盘)、支付系统等,旨在帮助读者掌握构建一个可扩展的系统所需的基础知识,为面试做好充分准备。
作为过来人,作者提出了应对面试题的“四步法”,即确定问题范围→总体设计→细节设计→总结,书中的案例基本上都是按照这个步骤进行解析的。这种独特的呈现方式,直接针对面试者在面试过程中可能遇到的问题,帮助他们厘清思路,有条不紊地作答。
通过本书,读者可以了解不同Web 应用的系统设计方案的要点及采用的技术,据此查漏补缺,补齐自己知识体系中的短板,为面试成功增添更多的可能。而对于已经是架构师的读者而言,书中的案例将为他们提供新的思路和灵感,有助于他们在面试中更加从容地展现自己的设计思路和实践经验。