Otsing: 8688 (arhiveeritud tooted)

Hõbesõrmus, Hõbe 925°, roodium (kate), Tsirkonid, Suurus: 16.5, 2.2 gr.

Unlock the future of cloud data engineering with generative and agentic AI on AWS.This hands-on guide shows you how to build intelligent, responsive data platforms using cutting-edge AI capabilities and modern AWS services.Learn to design next-generation data architectures—from data lakes and data mesh to scalable pipelines and real-time analytics. Discover how generative AI and agentic automation are transforming every aspect of enterprise data work: ingesting unstructured data, enabling semantic search with Retrieval-Augmented Generation (RAG), building autonomous data agents, and using natural language interfaces to turn business questions into instant insights.Author Justin J. Leto, PE, MBA, PMP, is a Principal Solutions Architect at AWS with over 20 years of experience in data engineering and AI. He doesn't just teach today's techniques—he prepares you for the future disruptions reshaping the field. His book is essential reading for current and aspiring data engineers, data analysts, data architects, engineering managers, CTOs, CDOs, and data-focused entrepreneurs looking to gain an edge over the competition.What You Will Learn: Master the core principles and practices of data engineering to build a long, successful career in the field. Accelerate your impact using AWS cloud services for scalable, modern data solutions. Explore how the role of the modern data engineer is evolving to support generative and agentic AI use cases. Develop a modern data strategy by working backwards from business goals to gain buy-in from CxO-level leadership. Design and deploy modern data architectures—including data lakes, data mesh, and data marts—and understand when to use each. Apply generative and agentic AI to enhance every stage of the data engineering lifecycle. Evaluate emerging data and AI technologies using proven methodology to separate real value from hype. Prepare for the future of data engineering powered by autonomous agents that scale enterprise impact. Who this Book Is For:Data engineers, analysts, architects, and tech leaders seeking practical guidance on AWS data engineering and generative AI, with or without prior cloud experience.

This book is a practical guide to harnessing Hugging Face's powerful transformers library, unlocking access to the largest open-source LLMs. By simplifying complex NLP concepts and emphasizing practical application, it empowers data scientists, machine learning engineers, and NLP practitioners to build robust solutions without delving into theoretical complexities.The book is structured into three parts to facilitate a step-by-step learning journey. Part One covers building production-ready LLM solutions introduces the Hugging Face library and equips readers to solve most of the common NLP challenges without requiring deep knowledge of transformer internals. Part Two focuses on empowering LLMs with RAG and intelligent agents exploring Retrieval-Augmented Generation (RAG) models, demonstrating how to enhance answer quality and develop intelligent agents. Part Three covers LLM advances focusing on expert topics such as model training, principles of transformer architecture and other cutting-edge techniques related to the practical application of language models. Each chapter includes practical examples, code snippets, and hands-on projects to ensure applicability to real-world scenarios. This book bridges the gap between theory and practice, providing professionals with the tools and insights to develop practical and efficient LLM solutions. What you will learn: What are the different types of tasks modern LLMs can solve How to select the most suitable pre-trained LLM for specific tasks How to enrich LLM with a custom knowledge base and build intelligent systems What are the core principles of Language Models, and how to tune them How to build robust LLM-based AI Applications Who this book is for:Data scientists, machine learning engineers, and NLP specialists with basic Python skills, introductory PyTorch knowledge, and a primary understanding of deep learning concepts, ready to start applying Large Language Models in practice.

This book is a complete, hands-on guide to designing, training, and deploying your own Large Language Models (LLMs)—from the foundations of tokenization to the advanced stages of fine-tuning and reinforcement learning. Written for developers, data scientists, and AI practitioners, it bridges core principles and state-of-the-art techniques, offering a rare, transparent look at how modern transformers truly work beneath the surface.Starting from the essentials, you’ll learn how to set up your environment with Python and PyTorch, manage datasets, and implement critical fundamentals such as tensors, embeddings, and gradient descent. You’ll then progress through the architectural heart of modern models, covering RMS normalization, rotary positional embeddings (RoPE), scaled dot-product attention, Grouped Query Attention (GQA), Mixture of Experts (MoE), and SwiGLU activations, each explored in depth and built step by step in code. As you advance, the book introduces custom CUDA kernel integration, teaching you how to optimize key components for speed and memory efficiency at the GPU level—an essential skill for scaling real-world LLMs. You’ll also gain mastery over the phases of training that define today’s leading models: Pretraining - Building general linguistic and semantic understanding. Midtraining - Expanding domain-specific capabilities and adaptability. Supervised Fine-Tuning (SFT) - Aligning behavior with curated, task-driven data. Reinforcement Learning from Human Feedback (RLHF) - Refining responses through reward-based optimization for human alignment. The final chapters guide you through dataset preparation, filtering, deduplication, and training optimization, culminating in model evaluation and real-world prompting with a custom TokenGenerator for text generation and inference.By the end of this book, you’ll have the knowledge and confidence to architect, train, and deploy your own transformer-based models, equipped with both the theoretical depth and practical expertise to innovate in the rapidly evolving world of AI.What You’ll Learn How to configure and optimize your development environment using PyTorch The mechanics of tokenization, embeddings, normalization, and attention mechanisms. How to implement transformer components like RMSNorm, RoPE, GQA, MoE, and SwiGLU from scratch. How to integrate custom CUDA kernels to accelerate transformer computations. The full LLM training pipeline: pretraining, midtraining, supervised fine-tuning, and RLHF. Techniques for dataset preparation, deduplication, model debugging, and GPU memory management. How to train, evaluate, and deploy a complete GPT-like architecture for real-world tasks. Who this book is for:Software developers, data scientists, machine learning engineers and AI enthusiasts looking to build their models from scratch.