GPT-3: NLP with LLMs is a unique, pragmatic take on Generative Pre-trained Transformer 3, the famous AI language model launched by OpenAI in 2020. This model is capable of tackling a wide array of tasks, like conversation, text completion, and even coding with stunningly good performance. Since its launch, the API has powered a staggering number of applications that have now grown into full-fledged startups generating business value. This book will be a deep dive into what GPT-3 is, why it is important, what it can do, what has already been done with it, how to get access to it, and how one can build a GPT-3 powered product from scratch.

This book is for anyone who wants to understand the scope and nature of GPT-3. The book will evaluate the GPT-3 API from multiple perspectives and discuss the various components of the new, burgeoning economy enabled by GPT-3. This book will look at the influence of GPT-3 on important AI trends like creator economy, no-code, and Artificial General Intelligence and will equip the readers to structure their imaginative ideas and convert them from mere concepts to reality.

Table of Contents

  1. 1. Era of Large Language Models
    1. Natural Language Processing: Under the Hood
    2. Language Models: Bigger & Better
    3. The Generative Pre-Trained Transformer: GPT-3
    4. Generative models
    5. Pre-trained models
    6. Transformer models
    7. Sequence-to-sequence models
    8. Transformers and attention mechanisms
    9. A Brief History of GPT-3
    10. Accessing the OpenAI API
  2. 2. Using the OpenAI API
    1. Navigating OpenAI Playground
    2. Prompt Engineering & Design
    3. Components of the OpenAI API
    4. Execution Engine
    5. Response Length
    6. Temperature and Top P
    7. Frequency and Presence Penalties
    8. Best Of
    9. Stop Sequence
    10. Inject Start Text and Inject Restart Text
    11. Show Probabilities
    12. Execution Engines
    13. Davinci
    14. Curie
    15. Babbage
    16. Ada
    17. Instruct Model Series
    18. Endpoints
    19. GPT-3 Fine-tuning
    20. Prepare and upload training data
    21. Train a new fine-tuned model
    22. Using the fine-tuned model
    23. Tokens
    24. Pricing
    25. Performance on Conventional NLP Tasks
    26. Text Classification
    27. Zero-Shot Classification
    28. Single Shot/ Few Shots Classification
    29. Batch Classification
    30. Named Entity Recognition
    31. Text Summarization
    32. Text Generation
    33. Summary
  3. Index