Generative AI with Python and PyTorch: Navigating the AI frontier with LLMs, Stable Diffusion, and next-gen AI applications

by Joseph Babcock, Raghav Bali

Overview

Master generative AI techniques to create images and text using Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), LSTMs, and Large Language Models (LLMs)

Key Features

• Implement real-world applications of LLMs and generative AI
• Use PEFT and LoRA to fine-tune models with a subset of the model weights to speed up training
• Enhance your LLM toolbox with Retrieval Augmented Generation (RAG) techniques, LangChain, and LlamaIndex
• Purchase of the print or Kindle book includes a free eBook in PDF format

Book Description

Become an expert in generative AI through practical projects to leverage cutting-edge models for Natural Language Processing (NLP) and computer vision. Generative AI with Python and PyTorch, Second Edition, is your comprehensive guide to creating advanced AI applications. Leveraging Python, this book provides a detailed exploration of the latest generative AI technologies. From NLP to image generation, this edition dives into practical applications and the underlying theories that enable these technologies. By integrating the latest advancements and applications of large language models, this book prepares you to design and implement powerful AI systems that transform data into actionable insights. You’ll build your LLM toolbox by learning about various models, tools, and techniques, including GPT-4, LangChain, RLHF, LoRA, and retrieval augmented generation. This deep learning book shows you how to generate images and apply styler transfer using GANs, before implementing CLIP and diffusion models. Whether you’re creating dynamic content or developing complex AI-driven solutions, Generative AI with Python and PyTorch, Second Edition, equips you with the knowledge to use Python and AI to their full potential.

What you will learn

• Understand the core concepts behind large language models and their capabilities
• Craft effective prompts using chain-of-thought, ReAct, and prompt query language to guide LLMs toward your desired outputs
• Learn how attention and transformers have changed NLP
• Optimize your diffusion models by combining them with VAEs
• Build several text generation pipelines based on LSTMs and LLMs
• Leverage the power of open-source LLMs, such as Llama and Mistral, for various tasks

Who this book is for

This book is for data scientists, machine learning engineers, and software developers seeking practical skills in building generative AI systems. A basic understanding of math and statistics and experience with Python coding is required.

Product Details

ISBN-13:	9781835884454
Publisher:	Packt Publishing
Publication date:	03/28/2025
Sold by:	Barnes & Noble
Format:	eBook
Pages:	450
File size:	37 MB
Note:	This product may take a few minutes to download.

About the Author

Joseph Babcock has spent over a decade working with big data and AI in the e-commerce, digital streaming, and quantitative finance domains. Throughout his career, he has worked on recommender systems, petabyte-scale cloud data pipelines, A/B testing, causal inference, and time series analysis. He completed his PhD studies at Johns Hopkins University, applying machine learning to drug discovery and genomics.
Raghav Bali is a Staff Data Scientist at Delivery Hero, a leading food delivery service headquartered in Berlin, Germany. With 12+ years of expertise, he specializes in research and development of enterprise-level solutions leveraging Machine Learning, Deep Learning, Natural Language Processing, and Recommendation Engines for practical business applications. Besides his professional endeavors, Raghav is an esteemed mentor and an accomplished public speaker. He has contributed to multiple peer-reviewed papers and authored multiple well received books. Additionally, he holds co-inventor credits on multiple patents in healthcare, machine learning, deep learning, and natural language processing.

Table of Contents

Table of Contents

1. Introduction to Generative AI: Drawing Data from Models
2. Building Blocks of Deep Neural Networks
3. The Rise of Methods for Text Generation
4. NLP 2.0: Using Transformers to Generate Text
5. LLM Foundations
6. Open-Source LLMs
7. Prompt Engineering
8. LLM Toolbox
9. LLM Optimization Techniques
10. Emerging Applications in Generative AI
11. Neural Networks Using VAEs
12. Image Generation with GANs
13. Style Transfer with GANs
14. Deepfakes with GANs
15. Diffusion Models and AI Art