The Practical, Step-by-Step Guide to Using LLMs at Scale in Projects and Products Large Language Models (LLMs) like Llama 3, Claude 3, and the GPT family are demonstrating breathtaking capabilities, but their size and complexity have deterred many practitioners from applying them. In Quick Start Guide to Large Language Models, Second Edition, pioneering data scientist and AI entrepreneur Sinan Ozdemir clears away those obstacles and provides a guide to working with, integrating, and deploying LLMs to solve practical problems. Ozdemir brings together all you need to get started, even if you have no direct experience with LLMs: step-by-step instructions, best practices, real-world case studies, and hands-on exercises. Along the way, he shares insights into LLMs' inner workings to help you optimize model choice, data formats, prompting, fine-tuning, performance, and much more. The resources on the companion website include sample datasets and up-to-date code for working with open- and closed-source LLMs such as those from OpenAI (GPT-4 and GPT-3.5), Google (BERT, T5, and Gemini), X (Grok), Anthropic (the Claude family), Cohere (the Command family), and&nbsp;Meta (BART and the LLaMA family). <ul> <li>Learn key concepts: pre-training, transfer learning, fine-tuning, attention, embeddings, tokenization, and more</li> <li>Use APIs and Python to fine-tune and customize LLMs for your requirements</li> <li>Build a complete neural/semantic information retrieval system and attach to conversational LLMs for building retrieval-augmented generation (RAG) chatbots and AI Agents</li> <li>Master advanced prompt engineering techniques like output structuring, chain-of-thought prompting, and semantic few-shot prompting</li> <li>Customize LLM embeddings to build a complete recommendation engine from scratch with user data that outperforms out-of-the-box embeddings from OpenAI</li> <li>Construct and fine-tune multimodal Transformer architectures from scratch using open-source LLMs and large visual datasets</li> <li>Align LLMs using Reinforcement Learning from Human and AI Feedback (RLHF/RLAIF) to build conversational agents from open models like Llama 3 and FLAN-T5</li> <li>Deploy prompts and custom fine-tuned LLMs to the cloud with scalability and evaluation pipelines in mind</li> <li>Diagnose and optimize LLMs for speed, memory, and performance with quantization, probing, benchmarking, and evaluation frameworks</li> </ul> "A refreshing and inspiring resource. Jam-packed with practical guidance and clear explanations that leave you smarter about this incredible new field." --Pete Huang, author of The Neuron Register your book for convenient access to downloads, updates, and/or corrections as they become available. See inside book for details.

Quick Start Guide to Large Language Models: Strategies and Best Practices for ChatGPT, Embeddings, Fine-Tuning, and Multimodal AI (Addison-Wesley Data & Analytics Series)

Computers & Technology

Ozdemir, Sinan

Computer Science

Addison-Wesley Professional

Quick Start Guide To Large Language Models: Strategies And Best Practices For Using Chatgpt, Embeddings, Fine-tuning, And Multimodal Ai

Addison-Wesley

The advancement of Large Language Models (LLMs) has revolutionized the field of Natural Language Processing in recent years. Models like BERT, T5, and ChatGPT have demonstrated unprecedented performance on a wide range of NLP tasks, from text classification to machine translation. Despite their impressive performance, the use of LLMs remains challenging for many practitioners. The sheer size of these models, combined with the lack of understanding of their inner workings, has made it difficult for practitioners to effectively use and optimize these models for their specific needs. Quick Start Guide to Large Language Models: Strategies and Best Practices for using ChatGPT and Other LLMs&nbsp;is a practical guide to the use of LLMs in NLP. It provides an overview of the key concepts and techniques used in LLMs and explains how these models work and how they can be used for various NLP tasks. The book also covers advanced topics, such as fine-tuning, alignment, and information retrieval while providing practical tips and tricks for training and optimizing LLMs for specific NLP tasks. This work addresses a wide range of topics in the field of Large Language Models, including the basics of LLMs, launching an application with proprietary models, fine-tuning GPT3 with custom examples, prompt engineering, building a recommendation engine, combining Transformers, and deploying custom LLMs to the cloud. It offers an in-depth look at the various concepts, techniques, and tools used in the field of Large Language Models. Topics covered: <ul> <li>Coding with Large Language Models (LLMs)</li> <li>Overview of using proprietary models</li> <li>OpenAI, Embeddings, GPT3, and ChatGPT</li> <li>Vector databases and building a neural/semantic information retrieval system</li> <li>Fine-tuning GPT3 with custom examples</li> <li>Prompt engineering with GPT3 and ChatGPT</li> <li>Advanced prompt engineering techniques</li> <li>Building a recommendation engine</li> <li>Combining Transformers</li> <li>Deploying custom LLMs to the cloud</li> </ul>

Quick Start Guide to Large Language Models: Strategies and Best Practices for Using ChatGPT and Other LLMs (Addison-Wesley Data & Analytics Series)

Praxiseinstieg Large Language Models: Strategien und Best Practices für den Einsatz von ChatGPT und anderen LLMs

Dpunkt

Deliver huge improvements to your machine learning pipelines without spending hours fine-tuning parameters! This book's practical case-studies reveal feature engineering techniques that upgrade your data wrangling--and your ML results. In Feature Engineering Bookcamp you will learn how to: &nbsp;&nbsp;&nbsp; Identify and implement feature transformations for your data &nbsp;&nbsp;&nbsp; Build powerful machine learning pipelines with unstructured data like text and images &nbsp;&nbsp;&nbsp; Quantify and minimize bias in machine learning pipelines at the data level &nbsp;&nbsp;&nbsp; Use feature stores to build real-time feature engineering pipelines &nbsp;&nbsp;&nbsp; Enhance existing machine learning pipelines by manipulating the input data &nbsp;&nbsp;&nbsp; Use state-of-the-art deep learning models to extract hidden patterns in data Feature Engineering Bookcamp guides you through a collection of projects that give you hands-on practice with core feature engineering techniques. You'll work with feature engineering practices that speed up the time it takes to process data and deliver real improvements in your model's performance. This instantly-useful book skips the abstract mathematical theory and minutely-detailed formulas; instead you'll learn through interesting code-driven case studies, including tweet classification, COVID detection, recidivism prediction, stock price movement detection, and more. Purchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications. About the technology Get better output from machine learning pipelines by improving your training data! Use feature engineering, a machine learning technique for designing relevant input variables based on your existing data, to simplify training and enhance model performance. While fine-tuning hyperparameters or tweaking models may give you a minor performance bump, feature engineering delivers dramatic improvements by transforming your data pipeline. About the book Feature Engineering Bookcamp walks you through six hands-on projects where you'll learn to upgrade your training data using feature engineering. Each chapter explores a new code-driven case study, taken from real-world industries like finance and healthcare. You'll practice cleaning and transforming data, mitigating bias, and more. The book is full of performance-enhancing tips for all major ML subdomains--from natural language processing to time-series analysis. What's inside &nbsp;&nbsp;&nbsp; Identify and implement feature transformations &nbsp;&nbsp;&nbsp; Build machine learning pipelines with unstructured data &nbsp;&nbsp;&nbsp; Quantify and minimize bias in ML pipelines &nbsp;&nbsp;&nbsp; Use feature stores to build real-time feature engineering pipelines &nbsp;&nbsp;&nbsp; Enhance existing pipelines by manipulating input data About the reader For experienced machine learning engineers familiar with Python. About the author Sinan Ozdemir is the founder and CTO of Shiba, a former lecturer of Data Science at Johns Hopkins University, and the author of multiple textbooks on data science and machine learning. Table of Contents 1 Introduction to feature engineering 2 The basics of feature engineering 3 Healthcare: Diagnosing COVID-19 4 Bias and fairness: Modeling recidivism 5 Natural language processing: Classifying social media sentiment 6 Computer vision: Object recognition 7 Time series analysis: Day trading with machine learning 8 Feature stores 9 Putting it all together

Feature Engineering Bookcamp

Manning

Key Features
<ul>
<li>Enhance your knowledge of coding with data science theory for practical insight into data science and analysis</li>
<li>More than just a math class, learn how to perform real-world data science tasks with R and Python</li>
<li>Create actionable insights and transform raw data into tangible value</li>
</ul>Book DescriptionNeed to turn your skills at programming into effective data science skills? Principles of Data Science is created to help you join the dots between mathematics, programming, and business analysis. With this book, you'll feel confident about asking―and answering―complex and sophisticated questions of your data to move from abstract and raw statistics to actionable ideas.
With a unique approach that bridges the gap between mathematics and computer science, this books takes you through the entire data science pipeline. Beginning with cleaning and preparing data, and effective data mining strategies and techniques, you'll move on to build a comprehensive picture of how every piece of the data science puzzle fits together. Learn the fundamentals of computational mathematics and statistics, as well as some pseudocode being used today by data scientists and analysts. You'll get to grips with machine learning, discover the statistical models that help you take control and navigate even the densest datasets, and find out how to create powerful visualizations that communicate what your data means.What you will learn<ul>
<li>Get to know the five most important steps of data science</li>
<li>Use your data intelligently and learn how to handle it with care</li>
<li>Bridge the gap between mathematics and programming </li>
<li>Learn about probability, calculus, and how to use statistical models to control and clean your data and drive actionable results</li>
<li>Build and evaluate baseline machine learning models</li>
<li>Explore the most effective metrics to determine the success of your machine learning models</li>
<li>Create data visualizations that communicate actionable insights</li>
<li>Read and apply machine learning concepts to your problems and make actual predictions</li>
</ul>About the AuthorSinan Ozdemir is a data scientist, startup founder, and educator living in the San Francisco Bay Area with his dog, Charlie; cat, Euclid; and bearded dragon, Fiero. He spent his academic career studying pure mathematics at Johns Hopkins University before transitioning to education. He spent several years conducting lectures on data science at Johns Hopkins University and at the General Assembly before founding his own start-up, Legion Analytics, which uses artificial intelligence and data science to power enterprise sales teams.
After completing the Fellowship at the Y Combinator accelerator, Sinan has spent most of his days working on his fast-growing company, while creating educational material for data science.Table of Contents<ol>
<li>How to Sound Like a Data Scientist</li>
<li>Types of Data</li>
<li>The Five Steps of Data Science</li>
<li>Basic Mathematics</li>
<li>Impossible or Improbable – A Gentle Introduction to Probability</li>
<li>Advanced Probability</li>
<li>Basic Statistics</li>
<li>Advanced Statistics</li>
<li>Communicating Data</li>
<li>How to Tell If Your Toaster Is Learning – Machine Learning Essentials</li>
<li>Predictions Don't Grow on Trees – or Do They?</li>
<li>Beyond the Essentials</li>
<li>Case Studies</li>
</ol>

Principles of Data Science: Mathematical techniques and theory to succeed in data-driven industries

Programming

Packt Publishing

A perfect guide to speed up the predicting power of machine learning algorithmsKey Features<ul>
<li>Design, discover, and create dynamic, efficient features for your machine learning application</li>
<li>Understand your data in depth and derive astonishing data insights with the help of this guide</li>
<li>Grasp powerful feature engineering techniques and build machine learning systems</li>
</ul>Book DescriptionFeature engineering is the most important step in creating powerful machine learning systems. This book will take you through the entire feature engineering journey to make machine learning much more systematic and effective.
You will start with understanding your data; often the success of your ML models depends on how you leverage different feature types, such as continuous, categorical, and more. You will learn when to include a feature, when to omit it, and why, all by understanding error analysis and the acceptability of your models. You will also learn to convert a problem statement into useful new features. This book will guide you in delivering features driven by business needs as well as mathematical insights, and you'll see how to use machine learning for your data.
By the end of the book, you will have become proficient in feature selection, feature learning, and feature pptimization.What you will learn<ul>
<li>Identify and leverage different feature types</li>
<li>Clean features in data to improve predictive power</li>
<li>Understand why and how to perform feature selection and model error analysis</li>
<li>Leverage domain knowledge to construct new features</li>
<li>Deliver features based on mathematical insights</li>
<li>Use machine learning algorithms to construct features</li>
<li>Master feature engineering and optimization</li>
<li>Harness feature engineering for real-world applications through a structured case study</li>
</ul>Who This Book Is ForIf you are a data science professional or a machine learning engineer looking to strengthen your predictive analytics model, then this book is a perfect guide for you. Some basic understanding of machine learning concepts and Python scripting would be enough to get started with this book.Table of Contents<ol>
<li>Introduction to Feature Engineering</li>
<li>Feature Understanding - What's in My Data?</li>
<li>Feature Improvement - Cleaning Datasets</li>
<li>Feature Construction</li>
<li>Feature Selection</li>
<li>Feature Transformation - How to Change Your Perspective</li>
<li>Feature Learning - Automatic Construction of Features</li>
<li>Putting It All Together</li>
</ol>

Feature Engineering Made Easy: Identify unique features from your dataset in order to build powerful machine learning systems

Susarla, Divya

Get into the world of smart data security using machine learning algorithms and Python libraries Key Features <ul>
<li>Learn machine learning algorithms and cybersecurity fundamentals </li> <li>Automate your daily workflow by applying use cases to many facets of security </li> <li>Implement smart machine learning solutions to detect various cybersecurity problems </li> </ul> Book Description Cyber threats today are one of the costliest losses that an organization can face. In this book, we use the most efficient tool to solve the big problems that exist in the cybersecurity domain. The book begins by giving you the basics of ML in cybersecurity using Python and its libraries. You will explore various ML domains (such as time series analysis and ensemble modeling) to get your foundations right. You will implement various examples such as building system to identify malicious URLs, and building a program to detect fraudulent emails and spam. Later, you will learn how to make effective use of K-means algorithm to develop a solution to detect and alert you to any malicious activity in the network. Also learn how to implement biometrics and fingerprint to validate whether the user is a legitimate user or not. Finally, you will see how we change the game with TensorFlow and learn how deep learning is effective for creating models and training systems What you will learn <ul>
<li>Use machine learning algorithms with complex datasets to implement cybersecurity concepts </li> <li>Implement machine learning algorithms such as clustering, k-means, and Naive Bayes to solve real-world problems </li> <li>Learn to speed up a system using Python libraries with NumPy, Scikit-learn, and CUDA </li> <li>Understand how to combat malware, detect spam, and fight financial fraud to mitigate cyber crimes </li> <li>Use TensorFlow in the cybersecurity domain and implement real-world examples </li> <li>Learn how machine learning and Python can be used in complex cyber issues</li>
</ul> Who this book is for This book is for the data scientists, machine learning developers, security researchers, and anyone keen to apply machine learning to up-skill computer security. Having some working knowledge of Python and being familiar with the basics of machine learning and cybersecurity fundamentals will help to get the most out of the bookTable of Contents <ol>
<li>Basics of Machine Learning in Cyber Security </li> <li>Time series analysis and Ensemble modelling</li> <li>Segregating legitimate and lousy URLs</li> <li>Knocking down captchas</li> <li>Using Data Science to catch email frauds and spams</li> <li>Efficient Network Anomaly detection using K Means </li> <li>Decision Tree and context based malicious event detection</li> <li>Catching impersonators and hackers red handed</li> <li>Change the game with Tensorflow</li> <li>Financial frauds and how deep learning can mitigate them</li> <li>Practical Case Studies in Cyber Security </li>
</ol>

Hands-On Machine Learning for Cybersecurity

Halder, Soma

See the best price to sell, buy, or rent books by Ozdemir, Sinan. BookScouter helps to compare book prices from 25+ online bookstores and 30+ buyback vendors with a single search.

Books by Ozdemir, Sinan