Scribd Logo
Upload

Welcome to Scribd!

  • 14 views

    Toc 9780138199302

    Uploaded by

    mgbdev

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Toc 9780138199302

    Uploaded by

    mgbdev
    14 views8 pages

    Original Title

    toc_9780138199302

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    14 views8 pages

    Toc 9780138199302

    Uploaded by

    mgbdev

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 8

    Praise for Quick Start Guide to Large Language Models

    “By balancing the potential of both open- and closed-source models, Quick Start Guide to Large
    Language Models stands as a comprehensive guide to understanding and using LLMs, bridging the
    gap between theoretical concepts and practical application.”
    —Giada Pistilli, Principal Ethicist at Hugging Face

    “A refreshing and inspiring resource. Jam-packed with practical guidance and clear explanations
    that leave you smarter about this incredible new field.”
    —Pete Huang, author of The Neuron

    “When it comes to building Large Language Models (LLMs), it can be a daunting task to find
    comprehensive resources that cover all the essential aspects. However, my search for such a
    resource recently came to an end when I discovered this book.
    “One of the stand-out features of Sinan is his ability to present complex concepts in a
    straightforward manner. The author has done an outstanding job of breaking down intricate
    ideas and algorithms, ensuring that readers can grasp them without feeling overwhelmed. Each
    topic is carefully explained, building upon examples that serve as steppingstones for better
    understanding. This approach greatly enhances the learning experience, making even the most
    intricate aspects of LLM development accessible to readers of varying skill levels.
    “Another strength of this book is the abundance of code resources. The inclusion of practical
    examples and code snippets is a game-changer for anyone who wants to experiment and apply
    the concepts they learn. These code resources provide readers with hands-on experience, allowing
    them to test and refine their understanding. This is an invaluable asset, as it fosters a deeper
    comprehension of the material and enables readers to truly engage with the content.
    “In conclusion, this book is a rare find for anyone interested in building LLMs. Its
    exceptional quality of explanation, clear and concise writing style, abundant code resources,
    and comprehensive coverage of all essential aspects make it an indispensable resource. Whether
    you are a beginner or an experienced practitioner, this book will undoubtedly elevate your
    understanding and practical skills in LLM development. I highly recommend Quick Start Guide
    to Large Language Models to anyone looking to embark on the exciting journey of building LLM
    applications.”
    —Pedro Marcelino, Machine Learning Engineer,
    Co-Founder and CEO @overfit.study

    “Ozdemir’s book cuts through the noise to help readers understand where the LLM revolution
    has come from—and where it is going. Ozdemir breaks down complex topics into practical
    explanations and easy to follow code examples.”
    —Shelia Gulati, Former GM at Microsoft and current Managing
    Director of Tola Capital
    Quick Start Guide to Large Language
    Models: Strategies and Best Practices
    for Using ChatGPT and Other LLMs

    Table of Contents

    Cover
    Half Title
    Title Page
    Copyright Page
    Table of Contents
    Foreword
    Preface
    Acknowledgments
    About the Author
    Part I: Introduction to Large Language Models
    1 Overview of Large Language Models
    What Are Large Language Models?
    Definition of LLMs
    Key Characteristics of LLMs
    How LLMs Work

    Popular Modern LLMs


    BERT
    GPT-3 and ChatGPT
    T5

    Domain-Specific LLMs
    Applications of LLMs
    Table of Contents
    Classical NLP Tasks
    Free-Text Generation
    Information Retrieval/Neural Semantic Search
    Chatbots

    Summary
    2 Semantic Search with LLMs
    Introduction
    The Task
    Asymmetric Semantic Search

    Solution Overview
    The Components
    Text Embedder
    Document Chunking
    Vector Databases
    Pinecone
    Open-Source Alternatives
    Re-ranking the Retrieved Results
    API

    Putting It All Together


    Performance

    The Cost of Closed-Source Components


    Summary
    3 First Steps with Prompt Engineering
    Introduction
    Prompt Engineering
    Alignment in Language Models
    Just Ask
    Few-Shot Learning
    Output Structuring
    Prompting Personas

    Working with Prompts Across Models


    Table of Contents
    ChatGPT
    Cohere
    Open-Source Prompt Engineering

    Building a Q/A Bot with ChatGPT


    Summary

    Part II: Getting the Most Out of LLMs


    4 Optimizing LLMs with Customized Fine-Tuning
    Introduction
    Transfer Learning and Fine-Tuning: A Primer
    The Fine-Tuning Process Explained
    Closed-Source Pre-trained Models as a Foundation

    A Look at the OpenAI Fine-Tuning API


    The GPT-3 Fine-Tuning API
    Case Study: Amazon Review Sentiment Classification
    Guidelines and Best Practices for Data

    Preparing Custom Examples with the OpenAI CLI


    Setting Up the OpenAI CLI
    Hyperparameter Selection and Optimization

    Our First Fine-Tuned LLM


    Evaluating Fine-Tuned Models with Quantitative Metrics
    Qualitative Evaluation Techniques
    Integrating Fine-Tuned GPT-3 Models into Applications

    Case Study: Amazon Review Category Classification


    Summary
    5 Advanced Prompt Engineering
    Introduction
    Prompt Injection Attacks
    Input/Output Validation
    Example: Using NLI to Build Validation Pipelines

    Batch Prompting
    Prompt Chaining
    Table of Contents
    Chaining as a Defense Against Prompt Injection
    Chaining to Prevent Prompt Stuffing
    Example: Chaining for Safety Using Multimodal LLMs

    Chain-of-Thought Prompting
    Example: Basic Arithmetic

    Revisiting Few-Shot Learning


    Example: Grade-School Arithmetic with LLMs

    Testing and Iterative Prompt Development


    Summary
    6 Customizing Embeddings and Model Architectures
    Introduction
    Case Study: Building a Recommendation System
    Setting Up the Problem and the Data
    Defining the Problem of Recommendation
    A 10,000-Foot View of Our Recommendation System
    Generating a Custom Description Field to Compare Items
    Setting a Baseline with Foundation Embedders
    Preparing Our Fine-Tuning Data
    Fine-Tuning Open-Source Embedders Using Sentence Transformers
    Summary of Results

    Summary

    Part III: Advanced LLM Usage


    7 Moving Beyond Foundation Models
    Introduction
    Case Study: Visual Q/A
    Introduction to Our Models: The Vision Transformer, GPT-2, and DistilBERT
    Hidden States Projection and Fusion
    Cross-Attention: What Is It, and Why Is It Critical?
    Our Custom Multimodal Model
    Our Data: Visual QA
    The VQA Training Loop
    Table of Contents
    Summary of Results

    Case Study: Reinforcement Learning from Feedback


    Our Model: FLAN-T5
    Our Reward Model: Sentiment and Grammar Correctness
    Transformer Reinforcement Learning
    The RLF Training Loop
    Summary of Results

    Summary
    8 Advanced Open-Source LLM Fine-Tuning
    Introduction
    Example: Anime Genre Multilabel Classification with BERT
    Using the Jaccard Score to Measure Performance for Multilabel Genre Prediction of
    Anime Titles
    A Simple Fine-Tuning Loop
    General Tips for Fine-Tuning Open-Source LLMs
    Summary of Results

    Example: LaTeX Generation with GPT2


    Prompt Engineering for Open-Source Models
    Summary of Results

    Sinans Attempt at Wise Yet Engaging Responses: SAWYER


    Step 1: Supervised Instruction Fine-Tuning
    Step 2: Reward Model Training
    Step 3: Reinforcement Learning from (Estimated) Human Feedback
    Summary of Results

    The Ever-Changing World of Fine-Tuning


    Summary
    9 Moving LLMs into Production
    Introduction
    Deploying Closed-Source LLMs to Production
    Cost Projections
    API Key Management

    Deploying Open-Source LLMs to Production


    Table of Contents
    Preparing a Model for Inference
    Interoperability
    Quantization
    Pruning
    Knowledge Distillation
    Cost Projections with LLMs
    Pushing to Hugging Face

    Summary
    Your Contributions Matter
    Keep Going!

    Part IV: Appendices


    A LLM FAQs
    B LLM Glossary
    C LLM Application Archetypes
    Index

    You might also like