You're reading from Transformers for Natural Language Processing Build, train, and fine-tune deep neural network architectures for NLP with Python, Hugging Face, and OpenAI's GPT-3, ChatGPT, and GPT-4

Product type Paperback

Published in Mar 2022

Publisher Packt

ISBN-13 9781803247335

Length 602 pages

Edition 2nd Edition

Languages

Processing

Tools

Processing

Concepts

Mobile Application Development

Author (1):

Denis Rothman

View More author details

Table of Contents (25) Chapters

Preface

1. What are Transformers?

2. Getting Started with the Architecture of the Transformer Model FREE CHAPTER

3. Fine-Tuning BERT Models

4. Pretraining a RoBERTa Model from Scratch

5. Downstream NLP Tasks with Transformers

6. Machine Translation with the Transformer

7. The Rise of Suprahuman Transformers with GPT-3 Engines

8. Applying Transformers to Legal and Financial Documents for AI Text Summarization

9. Matching Tokenizers and Datasets

10. Semantic Role Labeling with BERT-Based Transformers

11. Let Your Data Do the Talking: Story, Questions, and Answers

12. Detecting Customer Emotions to Make Predictions

13. Analyzing Fake News with Transformers

14. Interpreting Black Box Transformer Models

15. From NLP to Task-Agnostic Transformer Models

16. The Emergence of Transformer-Driven Copilots

17. The Consolidation of Suprahuman Transformers with OpenAI’s ChatGPT and GPT-4

18. Other Books You May Enjoy

19. Index

Appendix I — Terminology of Transformer Models

1. Appendix II — Hardware Constraints for Transformer Models

2. Appendix III — Generic Text Completion with GPT-2

3. Appendix IV — Custom Text Completion with GPT-2

4. Appendix V — Answers to the Questions

Running OpenAI GPT-3 tasks

In this section, we will run GPT-3 in two different ways:

We will first run the GPT-3 tasks online with no code
We will then implement GPT-3 in Google Colab notebook

We will be using GPT-3 engines in this book. When you sign up for the GPT-3 API, OpenAI gives you a free budget to get started. This free budget should cover most of the cost, if not all of the cost, of running the examples in this book once or twice.

Let’s begin by running NLP tasks online.

Running NLP tasks online

We will now go through some Industry 4.0 examples without an API, directly asking GPT-3 to do something for us.

Let us define a standard structure of a prompt and response as:

N = name of the NLP task (INPUT).
E = explanation for the GPT-3 engine. E precedes T (INPUT).
T = the text or content we wish GPT-3 to look into (INPUT).
S = showing GPT-3 what is expected. S follows T and is added when...

The rest of the chapter is locked

You're reading from Transformers for Natural Language Processing Build, train, and fine-tune deep neural network architectures for NLP with Python, Hugging Face, and OpenAI's GPT-3, ChatGPT, and GPT-4

Table of Contents (25) Chapters

Running OpenAI GPT-3 tasks

Running NLP tasks online

Unlock this book and the full library FREE for 7 days

Authors (1)