فهرست مطالب

• Cover
• Copyright
• Table of Contents
• Preface
• Chapter 1. Generative AI Use Cases, Fundamentals, and Project Life Cycle
• Use Cases and Tasks
• Foundation Models and Model Hubs
• Generative AI Project Life Cycle
• Generative AI on AWS
• Why Generative AI on AWS?
• Building Generative AI Applications on AWS
• Summary
• Chapter 2. Prompt Engineering and In-Context Learning
• Prompts and Completions
• Tokens
• Prompt Engineering
• Prompt Structure
• In-Context Learning with Few-Shot Inference
• Prompt-Engineering Best Practices
• Inference Configuration Parameters
• Summary
• Chapter 3. Large-Language Foundation Models
• Large-Language Foundation Models
• Tokenizers
• Embedding Vectors
• Transformer Architecture
• Types of Transformer-Based Foundation Models
• Pretraining Datasets
• Scaling Laws
• Compute-Optimal Models
• Summary
• Chapter 4. Memory and Compute Optimizations
• Memory Challenges
• Data Types and Numerical Precision
• Quantization
• Optimizing the Self-Attention Layers
• Distributed Computing
• Distributed Computing on AWS
• Summary
• Chapter 5. Fine-Tuning and Evaluation
• Instruction Fine-Tuning
• Instruction Dataset
• Instruction Fine-Tuning
• Evaluation
• Summary
• Chapter 6. Parameter-Efficient Fine-Tuning
• Full Fine-Tuning Versus PEFT
• LoRA and QLoRA
• Prompt Tuning and Soft Prompts
• Summary
• Chapter 7. Fine-Tuning with Reinforcement Learning from Human Feedback
• Human Alignment: Helpful, Honest, and Harmless
• Reinforcement Learning Overview
• Train a Custom Reward Model
• Existing Reward Model: Toxicity Detector by Meta
• Fine-Tune with Reinforcement Learning from Human Feedback
• Evaluate RLHF Fine-Tuned Model
• Summary
• Chapter 8. Model Deployment Optimizations
• Model Optimizations for Inference
• Large Model Inference Container
• AWS Inferentia: Purpose-Built Hardware for Inference
• Model Update and Deployment Strategies
• Metrics and Monitoring
• Autoscaling
• Summary
• Chapter 9. Context-Aware Reasoning Applications Using RAG and Agents
• Large Language Model Limitations
• Retrieval-Augmented Generation
• RAG Orchestration and Implementation
• Agents
• Generative AI Applications
• FMOps: Operationalizing the Generative AI Project Life Cycle
• Summary
• Chapter 10. Multimodal Foundation Models
• Use Cases
• Multimodal Prompt Engineering Best Practices
• Image Generation and Enhancement
• Inpainting, Outpainting, Depth-to-Image
• Image Captioning and Visual Question Answering
• Model Evaluation
• Diffusion Architecture Fundamentals
• Stable Diffusion 2 Architecture
• Stable Diffusion XL Architecture
• Summary
• Chapter 11. Controlled Generation and Fine-Tuning with Stable Diffusion
• ControlNet
• Fine-Tuning
• Human Alignment with Reinforcement Learning from Human Feedback
• Summary
• Chapter 12. Amazon Bedrock: Managed Service for Generative AI
• Bedrock Foundation Models
• Bedrock Inference APIs
• Large Language Models
• Fine-Tuning
• Agents
• Multimodal Models
• Data Privacy and Network Security
• Governance and Monitoring
• Summary
• Index
• About the Authors
• Colophon