فهرست مطالب

• Preface
• I. Understanding Language Models
• 1. An Introduction to Large Language Models
• What Is Language AI?
• A Recent History of Language AI
• The Moving Definition of a “Large Language Model”
• The Training Paradigm of Large Language Models
• Large Language Model Applications: What Makes Them So Useful?
• Responsible LLM Development and Usage
• Limited Resources Are All You Need
• Interfacing with Large Language Models
• Generating Your First Text
• Summary
• 2. Tokens and Embeddings
• LLM Tokenization
• Token Embeddings
• Text Embeddings (for Sentences and Whole Documents)
• Word Embeddings Beyond LLMs
• Embeddings for Recommendation Systems
• Summary
• 3. Looking Inside Large Language Models
• An Overview of Transformer Models
• Recent Improvements to the Transformer Architecture
• Summary
• II. Using Pretrained Language Models
• 4. Text Classification
• The Sentiment of Movie Reviews
• Text Classification with Representation Models
• Model Selection
• Using a Task-Specific Model
• Classification Tasks That Leverage Embeddings
• Text Classification with Generative Models
• Summary
• 5. Text Clustering and Topic Modeling
• ArXiv’s Articles: Computation and Language
• A Common Pipeline for Text Clustering
• From Text Clustering to Topic Modeling
• Summary
• 6. Prompt Engineering
• Using Text Generation Models
• Intro to Prompt Engineering
• Advanced Prompt Engineering
• Reasoning with Generative Models
• Output Verification
• Summary
• 7. Advanced Text Generation Techniques and Tools
• Model I/O: Loading Quantized Models with LangChain
• Chains: Extending the Capabilities of LLMs
• Memory: Helping LLMs to Remember Conversations
• Agents: Creating a System of LLMs
• Summary
• 8. Semantic Search and Retrieval-Augmented Generation
• Overview of Semantic Search and RAG
• Semantic Search with Language Models
• Retrieval-Augmented Generation (RAG)
• Summary
• 9. Multimodal Large Language Models
• Transformers for Vision
• Multimodal Embedding Models
• Making Text Generation Models Multimodal
• Summary
• III. Training and Fine-Tuning Language Models
• 10. Creating Text Embedding Models
• Embedding Models
• What Is Contrastive Learning?
• SBERT
• Creating an Embedding Model
• Fine-Tuning an Embedding Model
• Unsupervised Learning
• Summary
• 11. Fine-Tuning Representation Models for Classification
• Supervised Classification
• Few-Shot Classification
• Continued Pretraining with Masked Language Modeling
• Named-Entity Recognition
• Summary
• 12. Fine-Tuning Generation Models
• The Three LLM Training Steps: Pretraining, Supervised Fine-Tuning, and Preference Tuning
• Supervised Fine-Tuning (SFT)
• Instruction Tuning with QLoRA
• Evaluating Generative Models
• Preference-Tuning / Alignment / RLHF
• Automating Preference Evaluation Using Reward Models
• Preference Tuning with DPO
• Summary
• Afterword
• Index
• About the Authors