The advancement of Large Language Models (LLMs) has revolutionized the field of Natural Language Processing in recent years. Models like BERT, T5, and ChatGPT have demonstrated unprecedented performance on a wide range of NLP tasks, from text classification to machine translation. Despite their impressive performance, the use of LLMs remains challenging for many practitioners. The sheer size of these models, combined with the lack of understanding of their inner workings, has made it difficult for practitioners to effectively use and optimize these models for their specific needs.
Author(s): Sinan Ozdemir
Publisher: Addison-Wesley Professional
Year: 2023
Language: English
Commentary: early release, raw and unedited
Pages: 213
Title Page
Contents at a Glance
Table of Contents
Preface
Part I: Introduction to Large Language Models
1. Overview of Large Language Models
What Are Large Language Models (LLMs)?
Popular Modern LLMs
Domain-Specific LLMs
Applications of LLMs
Summary
2. Launching an Application with Proprietary Models
Introduction
The Task
Solution Overview
The Components
Putting It All Together
The Cost of Closed-Source
Summary
3. Prompt Engineering with GPT3
Introduction
Prompt Engineering
Working with Prompts Across Models
Building a Q/A bot with ChatGPT
Summary
4. Optimizing LLMs with Customized Fine-Tuning
Introduction
Transfer Learning and Fine-Tuning: A Primer
A Look at the OpenAI Fine-Tuning API
Preparing Custom Examples with the OpenAI CLI
Our First Fine-Tuned LLM!
Case Study 2: Amazon Review Category Classification
Summary
Part II: Getting the most out of LLMs
5. Advanced Prompt Engineering
Introduction
Prompt Injection Attacks
Input/Output Validation
Batch Prompting
Prompt Chaining
Chain of Thought Prompting
Re-visiting Few-shot Learning
Testing and Iterative Prompt Development
Conclusion
6. Customizing Embeddings and Model Architectures
Introduction
Case Study – Building a Recommendation System
Conclusion
7. Moving Beyond Foundation Models
Introduction
Case Study—Visual Q/A
Case Study—Reinforcement Learning from Feedback
Conclusion
8. Fine-Tuning Open-Source LLMs [This content is currently in development.]
9. Deploying Custom LLMs to the Cloud [This content is currently in development.]
