فهرست مطالب

• Copyright
• Table of Contents
• Preface
• Who This Book Is For
• How This Book Is Structured
• What This Book Is Not About
• How to Read the Book
• Conventions Used in This Book
• Using Code Examples
• O’Reilly Online Learning
• How to Contact Us
• Acknowledgments
• Part I. LLM Ingredients
• Chapter 1. Introduction
• Defining LLMs
• A Brief History of LLMs
• The Impact of LLMs
• LLM Usage in the Enterprise
• Prompting
• Accessing LLMs Through an API
• Strengths and Limitations of LLMs
• Building Your First Chatbot Prototype
• From Prototype to Production
• Summary
• Chapter 2. Pre-Training Data
• Ingredients of an LLM
• Pre-Training Data Requirements
• Popular Pre-Training Datasets
• Synthetic Pre-Training Data
• Training Data Preprocessing
• Effect of Pre-Training Data on Downstream Tasks
• Bias and Fairness Issues in Pre-Training Datasets
• Summary
• Chapter 3. Vocabulary and Tokenization
• Vocabulary
• Tokenizers
• Tokenization Pipeline
• Summary
• Chapter 4. Architectures and Learning Objectives
• Preliminaries
• Representing Meaning
• The Transformer Architecture
• Loss Functions
• Intrinsic Model Evaluation
• Transformer Backbones
• Learning Objectives
• Pre-Training Models
• Summary
• Part II. Utilizing LLMs
• Chapter 5. Adapting LLMs to Your Use Case
• Chapter 6. Fine-Tuning
• The Need for Fine-Tuning
• Fine-Tuning: A Full Example
• Fine-Tuning Datasets
• Summary
• Chapter 7. Advanced Fine-Tuning Techniques
• Continual Pre-Training
• Parameter-Efficient Fine-Tuning
• Combining Multiple Models
• Summary
• Chapter 8. Alignment Training and Reasoning
• Defining Alignment Training
• Reinforcement Learning
• Hallucinations
• Mitigating Hallucinations
• In-Context Hallucinations
• Hallucinations Due to Irrelevant Information
• Reasoning
• Inducing Reasoning in LLMs
• Summary
• Chapter 9. Inference Optimization
• LLM Inference Challenges
• Inference Optimization Techniques
• Techniques for Reducing Compute
• Techniques for Accelerating Decoding
• Techniques for Reducing Storage Needs
• Summary
• Part III. LLM Application Paradigms
• Chapter 10. Interfacing LLMs with External Tools
• LLM Interaction Paradigms
• Defining Agents
• Agentic Workflow
• Components of an Agentic System
• Summary
• Chapter 11. Representation Learning and Embeddings
• Introduction to Embeddings
• Semantic Search
• Similarity Measures
• Fine-Tuning Embedding Models
• Instruction Embeddings
• Optimizing Embedding Size
• Chunking
• Vector Databases
• Interpreting Embeddings
• Summary
• Chapter 12. Retrieval-Augmented Generation
• The Need for RAG
• Typical RAG Scenarios
• Deciding When to Retrieve
• The RAG Pipeline
• RAG for Memory Management
• RAG for Selecting In-Context Training Examples
• RAG for Model Training
• Limitations of RAG
• RAG Versus Long Context
• RAG Versus Fine-Tuning
• Summary
• Chapter 13. Design Patterns and System Architecture
• Multi-LLM Architectures
• Programming Paradigms
• Summary
• Index
• About the Author
• Colophon