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. 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 • 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 LLM Build 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. Purchase of the print book includes a free eBook in PDF and ePub formats from Manning Publications. About the technology Physicist Richard P. Feynman reportedly said, “I don’t understand anything I can’t build.” Based on this same powerful principle, bestselling author Sebastian Raschka guides you step by step as you build a GPT-style LLM that you can run on your laptop. This is an engaging book that covers each stage of the process, from planning and coding to training and fine-tuning. About the book Build a Large Language Model (From Scratch) 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! What's inside • Plan and code an LLM comparable to GPT-2 • Load pretrained weights • Construct a complete training pipeline • Fine-tune your LLM for text classification • Develop LLMs that follow human instructions About the reader Readers 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. The technical editor on this book was David Caswell. Table of Contents 1 Understanding large language models 2 Working with text data 3 Coding attention mechanisms 4 Implementing a GPT model from scratch to generate text 5 Pretraining on unlabeled data 6 Fine-tuning for classification 7 Fine-tuning to follow instructions A Introduction to PyTorch B References and further reading C Exercise solutions D Adding bells and whistles to the training loop E Parameter-efficient fine-tuning with LoRA Read more

Newly adapted for audiobook listeners.Data is at the center of many challenges in system design today. Difficult issues need to be figured out, such as scalability, consistency, reliability, efficiency, and maintainability. In addition, we have an overwhelming variety of tools, including relational databases, NoSQL datastores, stream or batch processors, and message brokers. What are the right choices for your application? How do you make sense of all these buzzwords?In this practical and comprehensive guide, author Martin Kleppmann helps you navigate this diverse landscape by examining the pros and cons of various technologies for processing and storing data. Software keeps changing, but the fundamental principles remain the same. With this book, software engineers and architects will learn how to apply those ideas in practice, and how to make full use of data in modern applications.Peer under the hood of the systems you already use, and learn how to use and operate them more effectively.Make informed decisions by identifying the strengths and weaknesses of different tools.Navigate the trade-offs around consistency, scalability, fault tolerance, and complexity.Understand the distributed systems research upon which modern databases are built.Peek behind the scenes of major online services, and learn from their architectures. Read more

The classic guide to how computers work, updated with new chapters and interactive graphics"For me, Code was a revelation. It was the first book about programming that spoke to me. It started with a story, and it built up, layer by layer, analogy by analogy, until I understood not just the Code, but the System. Code is a book that is as much about Systems Thinking and abstractions as it is about code and programming. Code teaches us how many unseen layers there are between the computer systems that we as users look at every day and the magical silicon rocks that we infused with lightning and taught to think."- Scott Hanselman, Partner Program Director, Microsoft, and host of HanselminutesComputers are everywhere, most obviously in our laptops and smartphones, but also our cars, televisions, microwave ovens, alarm clocks, robot vacuum cleaners, and other smart appliances. Have you ever wondered what goes on inside these devices to make our lives easier but occasionally more infuriating?For more than 20 years, readers have delighted in Charles Petzold's illuminating story of the secret inner life of computers, and now he has revised it for this new age of computing. Cleverly illustrated and easy to understand, this is the book that cracks the mystery. You'll discover what flashlights, black cats, seesaws, and the ride of Paul Revere can teach you about computing, and how human ingenuity and our compulsion to communicate have shaped every electronic device we use. This new expanded edition explores more deeply the bit-by-bit and gate-by-gate construction of the heart of every smart device, the central processing unit that combines the simplest of basic operations to perform the most complex of feats. Petzold's companion website, CodeHiddenLanguage.com, uses animated graphics of key circuits in the book to make computers even easier to comprehend. In addition to substantially revised and updated content, new chapters include:Chapter 18: Let's Build a Clock!Chapter 21: The Arithmetic Logic UnitChapter 22: Registers and BussesChapter 23: CPU Control SignalsChapter 24: Jumps, Loops, and CallsChapter 28: The World BrainFrom the simple ticking of clocks to the worldwide hum of the internet, Code reveals the essence of the digital revolution. Read more

None

COUNTERFEIT WARNING: Do NOT buy Used books - there is a 90% chance the 3rd party is selling pirated books filled with typos, missing SQL questions, and bad print quality. Only buy NEW!Authored by two Ex-Facebook employees, Ace the Data Science Interview is the best way to prepare for Data Science, Data Analyst, and Machine Learning interviews, so that you can land your dream job at FAANG, tech startups, or Wall Street.What's inside this 301 page book?201 real Data Science interview questions asked by Facebook, Google, Amazon, Netflix, Two Sigma, Citadel and more — with detailed step-by-step solutions!Learn how to break into Data Science, with tips on crafting your resume, creating kick-ass portfolio projects, sending networking cold emails, and better telling your story during behavioral interviewsQuestions cover the most frequently-tested topics in data interviews: Probability, Statistics, Machine Learning, SQL & Database Design, Coding (Python), Product Analytics, and A/B TestingEach chapter has a brief crash-course on the most important concepts and formulas to reviewLearn how to solve open-ended case study questions that combine product-sense, business intuition, and statistical modeling skills, and practice with case interviews from Airbnb, Instagram, & AccenturePraise for Ace the Data Science Interview:"The advice in this book directly helped me land my dream job" — Advitya Gemawat, ML Engineer, Microsoft“An invaluable resource for the Data Science & ML community”— Aishwarya Srinivasan, Senior Data Scientist, Google“Graduate students should read this book for a structured approach to prep for their next data Science interview”— Ali Gowani, Faculty at Northwestern University (MS in Data Science). “The authors explain exactly what hiring managers look for — a must read for any data job seeker”— Michelle Scarbrough, Former Data Analytics Manager, F500 Co."Super helpful career advice on breaking into data & landing your first job in the field"— Prithika Hariharan, President of Waterloo Data Science Club; Data Science Intern, Wish“FINALLY! Cracking the Coding Interview but for Data Science & ML!”— Jack Morris, AI Resident, Google“Solving the 201 interview questions is helpful for people in ALL industries, not just tech!”— Lars Hulstaert, Senior Data Scientist, Johnson & JohnsonAbout Kevin Huo:Kevin Huo is currently a Data Scientist at a Hedge Fund, and previously was a Data Scientist at Facebook working on Facebook Groups. He holds a degree in Computer Science from the University of Pennsylvania and a degree in Business from Wharton. In college he interned at Facebook, Bloomberg, and on Wall Street.About Nick Singh:Nick Singh previously worked on Facebook’s Growth Team and at SafeGraph, a geospatial analytics startup. Currently, he runs SQL interview platform DataLemur.com and shares career tips on LinkedIn to his 120,000+ followers. Nick holds a degree in System Engineering with a minor in Computer Science from the University of Virginia. In college, he interned at Microsoft and at Google’s Nest Labs on the Data Infrastructure Team. Read more

Reveal the insights behind your company’s data with Microsoft Power BI Microsoft Power BI allows intuitive access to data that can power intelligent business decisions and insightful strategies. The question is, do you have the Power BI skills to make your organization’s numbers spill their secrets? In Microsoft Power BI For Dummies, expert lecturer, consultant, and author Jack Hyman delivers a start-to-finish guide to applying the Power BI platform to your own firm’s data. You’ll discover how to start exploring your data sources, build data models, visualize your results, and create compelling reports that motivate decisive action. Tackle the basics of Microsoft Power BI and, when you’re done with that, move on to advanced functions like accessing data with DAX and app integrations Guide your organization’s direction and decisions with rock-solid conclusions based on real-world data Impress your bosses and confidently lead your direct reports with exciting insights drawn from Power BI’s useful visualization tools It’s one thing for your company to have data at its disposal. It’s another thing entirely to know what to do with it. Microsoft Power BI For Dummies is the straightforward blueprint you need to apply one of the most powerful business intelligence tools on the market to your firm’s existing data.   Read more

Use R to turn data into insight, knowledge, and understanding. With this practical book, aspiring data scientists will learn how to do data science with R and RStudio, along with the tidyverseâ??a collection of R packages designed to work together to make data science fast, fluent, and fun. Even if you have no programming experience, this updated edition will have you doing data science quickly. You'll learn how to import, transform, and visualize your data and communicate the results. And you'll get a complete, big-picture understanding of the data science cycle and the basic tools you need to manage the details. Updated for the latest tidyverse features and best practices, new chapters show you how to get data from spreadsheets, databases, and websites. Exercises help you practice what you've learned along the way. You'll understand how to: Visualize: Create plots for data exploration and communication of results Transform: Discover variable types and the tools to work with them Import: Get data into R and in a form convenient for analysis Program: Learn R tools for solving data problems with greater clarity and ease Communicate: Integrate prose, code, and results with Quarto Read more

NEW YORK TIMES BESTSELLER • A former Wall Street quant sounds the alarm on Big Data and the mathematical models that threaten to rip apart our social fabric—with a new afterword “A manual for the twenty-first-century citizen . . . relevant and urgent.”—Financial Times NATIONAL BOOK AWARD LONGLIST • NAMED ONE OF THE BEST BOOKS OF THE YEAR BY The New York Times Book Review • The Boston Globe • Wired • Fortune • Kirkus Reviews • The Guardian • Nature • On Point We live in the age of the algorithm. Increasingly, the decisions that affect our lives—where we go to school, whether we can get a job or a loan, how much we pay for health insurance—are being made not by humans, but by machines. In theory, this should lead to greater fairness: Everyone is judged according to the same rules. But as mathematician and data scientist Cathy O’Neil reveals, the mathematical models being used today are unregulated and uncontestable, even when they’re wrong. Most troubling, they reinforce discrimination—propping up the lucky, punishing the downtrodden, and undermining our democracy in the process. Welcome to the dark side of Big Data. Read more

None

Influence action through data! This is not a book. It is a one-of-a-kind immersive learning experience through which you can become—or teach others to be—a powerful data storyteller. Let's practice! helps you build confidence and credibility to create graphs and visualizations that make sense and weave them into action-inspiring stories. Expanding upon best seller storytelling with data's foundational lessons, Let's practice! delivers fresh content, a plethora of new examples, and over 100 hands-on exercises. Author and data storytelling maven Cole Nussbaumer Knaflic guides you along the path to hone core skills and become a well-practiced data communicator. Each chapter includes:● Practice with Cole: exercises based on real-world examples first posed for you to consider and solve, followed by detailed step-by-step illustration and explanation● Practice on your own: thought-provoking questions and even more exercises to be assigned or worked through individually, without prescribed solutions● Practice at work: practical guidance and hands-on exercises for applying storytelling with data lessons on the job, including instruction on when and how to solicit useful feedback and refine for greater impactThe lessons and exercises found within this comprehensive guide will empower you to master—or develop in others—data storytelling skills and transition your work from acceptable to exceptional. By investing in these skills for ourselves and our teams, we can all tell inspiring and influential data stories! Read more

Statistical methods are a key part of data science, yet few data scientists have formal statistical training. Courses and books on basic statistics rarely cover the topic from a data science perspective. The second edition of this popular guide adds comprehensive examples in Python, provides practical guidance on applying statistical methods to data science, tells you how to avoid their misuse, and gives you advice on what’s important and what’s not.Many data science resources incorporate statistical methods but lack a deeper statistical perspective. If you’re familiar with the R or Python programming languages and have some exposure to statistics, this quick reference bridges the gap in an accessible, readable format.With this book, you’ll learn:Why exploratory data analysis is a key preliminary step in data scienceHow random sampling can reduce bias and yield a higher-quality dataset, even with big dataHow the principles of experimental design yield definitive answers to questionsHow to use regression to estimate outcomes and detect anomaliesKey classification techniques for predicting which categories a record belongs toStatistical machine learning methods that "learn" from dataUnsupervised learning methods for extracting meaning from unlabeled data. Read more

To really learn data science, you should not only master the tools―data science libraries, frameworks, modules, and toolkits―but also understand the ideas and principles underlying them. Updated for Python 3.6, this second edition of Data Science from Scratch shows you how these tools and algorithms work by implementing them from scratch. If you have an aptitude for mathematics and some programming skills, author Joel Grus will help you get comfortable with the math and statistics at the core of data science, and with the hacking skills you need to get started as a data scientist. Packed with new material on deep learning, statistics, and natural language processing, this updated book shows you how to find the gems in today’s messy glut of data. Get a crash course in Python Learn the basics of linear algebra, statistics, and probability―and how and when they’re used in data science Collect, explore, clean, munge, and manipulate data Dive into the fundamentals of machine learning Implement models such as k-nearest neighbors, Naïve Bayes, linear and logistic regression, decision trees, neural networks, and clustering Explore recommender systems, natural language processing, network analysis, MapReduce, and databases Read more

Bring your data to life with this accessible yet fast-paced introduction to Power BI, now in color.Purchase of the print or Kindle book includes a free eBook in PDF format.Key Features: - Learn faster with practical examples of the latest features of Power BI, including navigator buttons, column-level security, visualizing goals, and more- Migrate your existing Excel and data analysis skills to Power BI- Build accurate analytical models, reports, and dashboards, now in colorBook Description: Updated with the latest features and improvements in Power BI, this fast-paced yet comprehensive guide will help you master the core concepts of data visualization quickly. You'll learn how to install Power BI, design effective data models, and build basic dashboards and visualizations to help you make better business decisions. This new edition will also help you bridge the gap between MS Excel and Power BI.Throughout this book, you'll learn how to obtain data from a variety of sources and clean it using the Power Query Editor. You'll also start designing data models to navigate and explore relationships within your data and building DAX formulas to make data easier to work with. Visualizing data is a key element of this book, so there's an emphasis on helping you get to grips with data visualization styles and enhanced digital storytelling.As you progress, you'll start building your own dataflows, gain an understanding of the Common Data Model, and automate dataflow refreshes to eradicate data cleaning inefficiency. You'll learn how to administer your organization's Power BI environment so that deployment can be made seamless, data refreshes can run properly, and security can be fully implemented.By the end of this Power BI book, you'll know how to get the most out of Power BI for better business intelligence.What You Will Learn: - Connect to data sources using import, DirectQuery, and live connection options- Use Power Query Editor for data transformation and data cleansing processes, and write M and R scripts and dataflows to do the same in the cloud- Design effective reports with built-in and custom visuals to optimize user experience- Implement row-level and column-level security in your dashboards- Administer a Power BI cloud tenant for your organization- Use built-in AI capabilities to enhance Power BI data transformation techniques- Deploy your Power BI Desktop files into Power BI Report ServerWho this book is for: This book is for aspiring business intelligence and data professionals with a basic understanding of BI concepts, who want to learn Power BI quickly. Complete beginners with no BI background can also get plenty of useful information from this book.Table of Contents- Gaining Data Literacy with Power BI- Connecting to Data- Data Transformation Strategies- Building the Data Model- Leveraging DAX- Visualizing Data- Digital Storytelling with Power BI- Using a Cloud Deployment with the Power BI Service- Data Cleansing in the Cloud with Dataflows- On-Premises Solutions with Power BI Report Server Read more

Leverage cutting-edge generative AI techniques such as RAG to realize the potential of your data and drive innovation as well as gain strategic advantageKey FeaturesOptimize data retrieval and generation using vector databasesBoost decision-making and automate workflows with AI agentsOvercome common challenges in implementing real-world RAG systemsPurchase of the print or Kindle book includes a free PDF eBookBook DescriptionGenerative AI is helping organizations tap into their data in new ways, with retrieval-augmented generation (RAG) combining the strengths of large language models (LLMs) with internal data for more intelligent and relevant AI applications. The author harnesses his decade of ML experience in this book to equip you with the strategic insights and technical expertise needed when using RAG to drive transformative outcomes.The book explores RAG’s role in enhancing organizational operations by blending theoretical foundations with practical techniques. You’ll work with detailed coding examples using tools such as LangChain and Chroma’s vector database to gain hands-on experience in integrating RAG into AI systems. The chapters contain real-world case studies and sample applications that highlight RAG’s diverse use cases, from search engines to chatbots. You’ll learn proven methods for managing vector databases, optimizing data retrieval, effective prompt engineering, and quantitatively evaluating performance. The book also takes you through advanced integrations of RAG with cutting-edge AI agents and emerging non-LLM technologies.By the end of this book, you’ll be able to successfully deploy RAG in business settings, address common challenges, and push the boundaries of what’s possible with this revolutionary AI technique.What you will learnUnderstand RAG principles and their significance in generative AIIntegrate LLMs with internal data for enhanced operationsMaster vectorization, vector databases, and vector search techniquesDevelop skills in prompt engineering specific to RAG and design for precise AI responsesFamiliarize yourself with AI agents' roles in facilitating sophisticated RAG applicationsOvercome scalability, data quality, and integration issuesDiscover strategies for optimizing data retrieval and AI interpretabilityWho this book is forThis book is for AI researchers, data scientists, software developers, and business analysts looking to leverage RAG and generative AI to enhance data retrieval, improve AI accuracy, and drive innovation. It is particularly suited for anyone with a foundational understanding of AI who seeks practical, hands-on learning. The book offers real-world coding examples and strategies for implementing RAG effectively, making it accessible to both technical and non-technical audiences. A basic understanding of Python and Jupyter Notebooks is required.Table of ContentsWhat Is Retrieval-Augmented Generation (RAG)Code Lab – An Entire RAG PipelinePractical Applications of RAGComponents of a RAG SystemManaging Security in RAG ApplicationsInterfacing with RAG and GradioThe Key Role Vectors and Vector Stores Play in RAGSimilarity Searching with VectorsEvaluating RAG Quantitatively and with VisualizationsKey RAG Components in LangChainUsing LangChain to Get More from RAGCombining RAG with the Power of AI Agents and LangGraphUsing Prompt Engineering to Improve RAG EffortsAdvanced RAG-Related Techniques for Improving Results Read more

The first book that delivers data viz best practices precisely for Power BIThis practical guide shows how to quickly create visualizations and build savvy dashboards, with 25 chapters that explore different chart types plus 40 visuals from the AppSource gallery, from default to advanced, all over 400 color pages.Key features:Beautiful examples of charts, along with specific use casesStep-by-step instruction on how to set up visuals in the appData preparation tips and tricksQuizzes to consolidate the learning materialData Visualization with Microsoft Power BI is suitable for both experienced data analysts and nontechnical professionals in finance, sales, and marketing. Here's what's inside:Part 1: Classic visuals. Discover how to choose charts for basic types of analysis and avoid common mistakes, then learn how to set up interactions and put visuals together on a dashboard.Part 2: Trusted advanced visuals. Explore different options and data requirements for charts and diagrams including waterfall, bullet, Gantt, tornado, funnel, Sankey, and more.Part 3: Risky advanced visuals. Consider eye-catching charts that nonetheless may confuse the average user, examine use cases, and understand how to avoid pitfalls or suggest simpler alternatives.You get "two in one":Data viz best practices, based on know-how cultivated over 15 years in the field of business intelligenceTechnical expertise along with clear guides and shortcuts derived from 300+ dashboards developed Read more

None

What value does semantic data modeling offer? As an information architect or data science professional, let’s say you have an abundance of the right data and the technology to extract business gold—but you still fail. The reason? Bad data semantics. In this practical and comprehensive field guide, author Panos Alexopoulos takes you on an eye-opening journey through semantic data modeling as applied in the real world. You’ll learn how to master this craft to increase the usability and value of your data and applications. You’ll also explore the pitfalls to avoid and dilemmas to overcome for building high-quality and valuable semantic representations of data. Understand the fundamental concepts, phenomena, and processes related to semantic data modeling Examine the quirks and challenges of semantic data modeling and learn how to effectively leverage the available frameworks and tools Avoid mistakes and bad practices that can undermine your efforts to create good data models Learn about model development dilemmas, including representation, expressiveness and content, development, and governance Organize and execute semantic data initiatives in your organization, tackling technical, strategic, and organizational challenges Read more

Data is bigger, arrives faster, and comes in a variety of formatsâ??and it all needs to be processed at scale for analytics or machine learning. But how can you process such varied workloads efficiently? Enter Apache Spark. Updated to include Spark 3.0, this second edition shows data engineers and data scientists why structure and unification in Spark matters. Specifically, this book explains how to perform simple and complex data analytics and employ machine learning algorithms. Through step-by-step walk-throughs, code snippets, and notebooks, youâ??ll be able to: Learn Python, SQL, Scala, or Java high-level Structured APIs Understand Spark operations and SQL Engine Inspect, tune, and debug Spark operations with Spark configurations and Spark UI Connect to data sources: JSON, Parquet, CSV, Avro, ORC, Hive, S3, or Kafka Perform analytics on batch and streaming data using Structured Streaming Build reliable data pipelines with open source Delta Lake and Spark Develop machine learning pipelines with MLlib and productionize models using MLflow Read more

Through a recent series of breakthroughs, deep learning has boosted the entire field of machine learning. Now, even programmers who know close to nothing about this technology can use simple, efficient tools to implement programs capable of learning from data. This bestselling book uses concrete examples, minimal theory, and production-ready Python frameworks (Scikit-Learn, Keras, and TensorFlow) to help you gain an intuitive understanding of the concepts and tools for building intelligent systems.With this updated third edition, author Aurélien Géron explores a range of techniques, starting with simple linear regression and progressing to deep neural networks. Numerous code examples and exercises throughout the book help you apply what you've learned. Programming experience is all you need to get started.Use Scikit-learn to track an example ML project end to endExplore several models, including support vector machines, decision trees, random forests, and ensemble methodsExploit unsupervised learning techniques such as dimensionality reduction, clustering, and anomaly detectionDive into neural net architectures, including convolutional nets, recurrent nets, generative adversarial networks, autoencoders, diffusion models, and transformersUse TensorFlow and Keras to build and train neural nets for computer vision, natural language processing, generative models, and deep reinforcement learning Read more

When it comes to choosing, using, and maintaining a database, understanding its internals is essential. But with so many distributed databases and tools available today, it’s often difficult to understand what each one offers and how they differ. With this practical guide, Alex Petrov guides developers through the concepts behind modern database and storage engine internals.Throughout the book, you’ll explore relevant material gleaned from numerous books, papers, blog posts, and the source code of several open source databases. These resources are listed at the end of parts one and two. You’ll discover that the most significant distinctions among many modern databases reside in subsystems that determine how storage is organized and how data is distributed.This book examines:Storage engines: Explore storage classification and taxonomy, and dive into B-Tree-based and immutable Log Structured storage engines, with differences and use-cases for eachStorage building blocks: Learn how database files are organized to build efficient storage, using auxiliary data structures such as Page Cache, Buffer Pool and Write-Ahead LogDistributed systems: Learn step-by-step how nodes and processes connect and build complex communication patternsDatabase clusters: Which consistency models are commonly used by modern databases and how distributed storage systems achieve consistency Read more