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.
Ivan Gridin is an artificial intelligence expert, researcher, and author with extensive experience in applying advanced machine-learning techniques in real-world scenarios. His expertise includes natural language processing (NLP), predictive time series modeling, automated machine learning (AutoML), reinforcement learning, and neural architecture search. He also has a strong foundation in mathematics, including stochastic processes, probability theory, optimization, and deep learning. In recent years, he has become a specialist in open-source large language models, including the Hugging Face framework. Building on this expertise, he continues to advance his work in developing intelligent, real-world applications powered by natural language processing.
He is a loving husband and father and collector of old math books.
You can learn more about him on LinkedIn: https://www.linkedin.com/in/survex/.
