|
 |
|
 |
|
|
 |
|  |
|
 Название: Large Language Models: A Deep Dive: Bridging Theory and Practice
Автор: Uday Kamath, Kevin Keenan, Garrett Somers
Издательство: Springer
Год: 2024
Страниц: 496
Язык: английский
Формат: pdf (true)
Размер: 30.7 MB
Large Language Models (LLMs) have emerged as a cornerstone technology, transforming how we interact with information and redefining the boundaries of Artificial Intelligence (AI). LLMs offer an unprecedented ability to understand, generate, and interact with human language in an intuitive and insightful manner, leading to transformative applications across domains like content creation, chatbots, search engines, and research tools. This book provides an authoritative exploration of the design, training, evolution, and application of LLMs. It begins with an overview of pre-trained language models and Transformer architectures, laying the groundwork for understanding prompt-based learning techniques. Next, it dives into methods for fine-tuning LLMs, integrating reinforcement learning for value alignment, and the convergence of LLMs with computer vision, robotics, and speech processing. The book strongly emphasizes practical applications, detailing real-world use cases such as conversational chatbots, retrieval-augmented generation (RAG), and code generation. These examples are carefully chosen to illustrate the diverse and impactful ways LLMs are being applied in various industries and scenarios. Not surprisingly, LLMs are highly competent at generating computer programming language and natural language. The most popular solution in this space is Github Copilot, which was designed to assist human programmers in developing software using computer code. Since it is the most popular solution in this space, below we will look at its core capabilities as an exemplar of the types of benefits that these types of LLM-enabled applications provide. Multiple programming language support allows developers to interoperate across coding languages efficiently. This capability is most useful in full-stack or specialist-domain application development, where multiple programming languages are used for different solution components. Imagine a full-stack developer writing data handling routines in jаvascript for the user interface. At the same time, Copilot suggests code blocks in Python for the back-end API that serves the data to the front-end. | |
Разместил: Ingvar16 21-08-2024, 18:28 | Комментарии: 0 | Подробнее
| | | |
 |
|  |
|
|
|
|
|
|
| |
|
 Название: Data Storytelling with Altair and AI (Final Release)
Автор: Angelica Lo Duca
Издательство: Manning Publications
Год: 2024
Страниц: 386
Язык: английский
Формат: pdf (true)
Размер: 11.1 MB
Great data presentations tell a story. Learn how to organize, visualize, and present data using Python, generative AI, and the cutting-edge Altair data visualization toolkit. Take the fast track to amazing data presentations! Data Storytelling with Altair and AI introduces a stack of useful tools and tried-and-tested methodologies that will rapidly increase your productivity, streamline the visualization process, and leave your audience inspired. Data Storytelling with Altair and AI teaches you how to turn raw data into effective, insightful data stories. You’ll learn exactly what goes into an effective data story, then combine your Python data skills with the Altair library and AI tools to rapidly create amazing visualizations. Your bosses and decision-makers will love your new presentations—and you’ll love how quick Generative AI makes the whole process! Every dataset tells a story. After you’ve cleaned, crunched, and organized the raw data, it’s your job to share its story in a way that connects with your audience. Python’s Altair data visualization library, combined with generative AI tools like Copilot and ChatGPT, provide an amazing toolbox for transforming numbers, code, text, and graphics into intuitive data presentations. For data analysts and data scientists experienced with Python. No previous knowledge of Altair or Generative AI required. | |
Разместил: Ingvar16 21-08-2024, 17:03 | Комментарии: 0 | Подробнее
| | | |
|
| |
|
|
|
|
|
|
| |
|
 Название: Idiomatic Rust: Code like a Rustacean (Final Release)
Автор: Brenden Matthews
Издательство: Manning Publications
Год: 2024
Страниц: 257
Язык: английский
Формат: pdf (true)
Размер: 10.1 MB
Build stable, maintainable Rust applications by applying these important code and architectural design patterns. Rust Advanced Techniques introduces reusable best practices that will help you solve common programming problems and ensure your code is easy for others to understand. Learn when to use each design pattern, as well as when to break it. This practical guide catalogs, documents, and describes both how classic design patterns work with Rust, and the new Rust-specific patterns that will help you master the language. Rust Advanced Techniques presents dozens of established programming and architecture solutions that take advantage of Rust’s unique language design. You’ll start with the basics of generics and traits, using them as a foundation to rapidly progress to metaprogramming, building your own libraries, and even advanced patterns like fluent interfaces and making immutable structures. Throughout this unique book, you’ll find useful code samples that are easy to adapt and reuse for your own projects. Hone your Rust skills with functional programming techniques, and explore examples of common anti-patterns so you know mistakes to avoid. You’ll soon have an in-depth understanding of when and how to apply each design pattern, and even create your very own! For the more advanced Rust programmers. Experienced Rustceans will benefit from tips and tricks that help speed up delivery and make full use of Rust’s lesser-known features. | |
Разместил: Ingvar16 21-08-2024, 16:29 | Комментарии: 0 | Подробнее
| | | |
|
| |
|
|
|
|
|
|
| |
|
 Название: AI-Powered Developer: Build great software with ChatGPT and Copilot (Final Release)
Автор: Nathan B. Crocker
Издательство: Manning Publications
Год: 2024
Страниц: 242
Язык: английский
Формат: pdf (true)
Размер: 21.1 MB
Use groundbreaking generative AI tools to increase your productivity, efficiency, and code quality. You just got a promotion! AI coding tools like GitHub Copilot, ChatGPT, and Amazon CodeWhisperer turn every developer into an engineering manager, overseeing a super-smart and super-fast junior coder. AI-Powered Developer demonstrates effective techniques and best practices for getting the most out of AI-powered coding using tools like Copilot and ChatGPT. The book cuts through the hype, showcasing real-world examples of how these tools ease and enhance your everyday tasks. You’ll soon be using AI for everything from writing boilerplate to assisting with software design. AI-Powered Developer shows you how to put AI coding tools like Github Copilot and ChatGPT into action. Throughout the book, you’ll generate code and design ideas as you build an IT Asset Management system using AI in every step of the development process. Clear advice and hands-on examples show you how to integrate these tools into your daily workflow. You’ll create self-documenting applications, generate predictive suggestions, and even use AI to test and explain your code. This practical book helps you develop an instinct for AI code and an understanding of what problems AI can and can’t solve. You’ll soon be confident in your transition to this new way to build software, aided by your diligent team of AI assistants. For software developers familiar with Python. | |
Разместил: Ingvar16 21-08-2024, 16:02 | Комментарии: 0 | Подробнее
| | | |
|
| |
|
|
|
|
|
|
| |
|
Название: Docker для начинающих: Шаг за шагом
Автор: Максим Дуплей
Издательство: Stepik
Год: 2024
Формат: PDF
Страниц: много
Размер: 12 Mb
Язык: Русский
Docker для начинающих: Шаг за шагом - предназначен для разработчиков, системных администраторов и DevOps-специалистов, желающих освоить современный инструмент для контейнеризации приложений.
| |
Разместил: Chipa 21-08-2024, 13:40 | Комментарии: 0 | Подробнее
| | | |
|
| |
|
|
|
|
|
|
| |
|
 Название: Large Language Models: Concepts, Techniques and Applications
Автор: John Atkinson‑Abutridy
Издательство: CRC Press
Год: 2025
Страниц: 185
Язык: английский
Формат: pdf (true)
Размер: 10.15 MB
This book serves as an introduction to the science and applications of Large Language Models (LLMs). You'll discover the common thread that drives some of the most revolutionary recent applications of Artificial Intelligence (AI): from conversational systems like ChatGPT or BARD, to machine translation, summary generation, question answering, and much more. At the heart of these innovative applications is a powerful and rapidly evolving discipline, natural language processing (NLP). For more than 60 years, research in this science has been focused on enabling machines to efficiently understand and generate human language. The secrets behind these technological advances lie in LLMs, whose power lies in their ability to capture complex patterns and learn contextual representations of language. How do these LLMs work? What are the available models and how are they evaluated? This book will help you answer these and many other questions. Designed to guide you step by step, with six chapters combining theory and practice, along with exercises in Python on the Colab platform, you will master the secrets of LLMs and their application in NLP. From deep neural networks and attention mechanisms, to the most relevant LLMs such as BERT, GPT-4, LLaMA, Palm-2 and Falcon, this book guides you through the most important achievements in NLP. Not only will you learn the benchmarks used to evaluate the capabilities of these models, but you will also gain the skill to create your own NLP applications. It will be of great value to professionals, researchers and students within AI, Data Science and beyond. | |
Разместил: Ingvar16 21-08-2024, 07:41 | Комментарии: 0 | Подробнее
| | | |
|
| |
|
|
|
|
|
|
| |
|
 Название: Learn Linux system programming with C++: Understand how the Linux kernel works and how to interact with it
Автор: Katie Millie
Издательство: Independently published
Год: 2024
Страниц: 276
Язык: английский
Формат: epub
Размер: 10.1 MB
Learn Linux System Programming with C++: Unlocking the Kernel's Secrets. Are you ready to dive deep into the heart of your computer? Linux, the operating system that powers everything from smartphones to supercomputers, is a complex and fascinating world. To truly master it, you need to understand how it interacts with hardware at the lowest level. That's where system programming comes in. This book is your passport to this exciting domain. You'll learn to wield the power of C++, the language of choice for kernel development, to interact directly with the Linux kernel. Imagine being able to create high-performance network applications, develop custom device drivers, or optimize system performance. With a deep understanding of Linux system programming, these aren't just dreams, they're achievable goals. We'll start from the ground up, covering essential concepts like system calls, process management, memory management,and file I/O. You'll learn how to interact with the kernel, create user-space applications, and even explore the world of kernel modules. C++ offers the power and flexibility to interact directly with hardware, making it the language of choice for performance-critical applications. Linux, with its open-source philosophy and rich ecosystem, provides the perfect platform for exploration and innovation. Together, they form an unstoppable duo. But this isn't just about theory. Practical examples and hands-on exercises will solidify your understanding. You'll build real-world projects, from simple command-line tools to more complex system utilities. | |
Разместил: Ingvar16 21-08-2024, 07:04 | Комментарии: 0 | Подробнее
| | | |
|
| |
|
|
|
|
|
|
| |
|
 Название: Getting Started with Docker
Автор: Nigel Poulton
Издательство: Leanpub
Год: 2024-04-06
Страниц: 109
Язык: английский
Формат: pdf (true), epub
Размер: 18.5 MB
Brought to you by best-selling author and global training guru Nigel Poulton, Getting Started with Docker is the fastest way to wrap your head around Docker and containers, and get your hands-on deploying a multi-container apps. When you've finished the book, you'll be ready to rock 'n' roll with Docker. Do you need to lear Docker, and do you like learning through hands-on? If yes, this is the book for you... Getting Started with Docker, brought to you by best-selling author Nigel Poulton, assumes zero prior experience and gets you to the point you can containerize and deploy a simple multi-container app. Containers are the most popular way to package and run modern applications. They’re smaller, faster, and more portable than virtual machines, and they work with existing applications written in existing languages – no need to learn any new languages or frameworks! The process of packaging an application as an image is called containerization. It takes the application source code, including all dependencies, and builds it into an image. This image is usually small and contains everything needed to run the app. When you're done, you'll be ready to start using Docker at work. | |
Разместил: Ingvar16 20-08-2024, 20:49 | Комментарии: 0 | Подробнее
| | | |
|
| |
|
|
|
|
|
|
| |
|
 Название: C++20 - Get the Details
Автор: Rainer Grimm
Издательство: Leanpub
Год: 2023-09-13
Страниц: 678
Язык: английский
Формат: pdf (true), epub
Размер: 25.1 MB
C++20 is the next big C++ standard after C++11. As C++11 did it, C++20 changes the way we program modern C++. This change is, in particular, due to the big four of C++20: ranges, coroutines, concepts, and modules. My book C++20 is a tutorial and a reference for the C++20 standard. It teaches you C++20 and provides details of this new, thrilling C++ standard. The exciting factor is mainly due to the big four of C++20. As the C++20 standard is brand-new, many examples can only be compiled and executed with a specific compiler. I use the newest GCC, Clang, and MSVC compilers. Coroutines are generalized functions that can be suspended and resumed later while maintaining their state. Coroutines are a convenient way to write event-driven applications. Event-driven applications can be simulations, games, servers, user interfaces, or even algorithms. Coroutines are also typically used for cooperative multitasking. C++20 does not provide concrete coroutines, but C++20 provides a framework for implementing coroutines. This framework consists of more than 20 functions, and some of which you must implement, some of which you can override. Therefore, you can tailor coroutines to your needs. | |
Разместил: Ingvar16 20-08-2024, 19:58 | Комментарии: 0 | Подробнее
| | | |
|
| |
|
|
|
|
|
|
| |
|
Название: Сборка проектов с помощью CMake
Автор: Воронин С.П.
Издательство: Самиздат
Год: 2024
Страниц: 21
Язык: Русский
Формат: PDF
Размер: 5 Mб
В статье рассмотрен необходимый минимум сведений о CMake, необходимый для сборки проекта. Показано, как использование CMake, упрощает процесс сборки сложных приложений, использующих сторонние и самописные библиотеки. Рассмотрен процесс сборки разными компиляторами и под различные операционные системы.
Что такое CMake? Можно ли без него обойтись? Порядок работы и особенности синтаксиса. Самые необходимые команды. Переменные в CMake. Как подключить библиотеки? Кроссплатформенная разработка. | |
Разместил: Gena_Bukin 20-08-2024, 19:29 | Комментарии: 0 | Подробнее
| | | |
|
| |
|
Навигация
Вход на сайт
Реклама
