You're reading from Mastering NLP from Foundations to LLMs Apply advanced rule-based techniques to LLMs and solve real-world business problems using Python

Product type Paperback

Published in Apr 2024

Publisher Packt

ISBN-13 9781804619186

Length 340 pages

Edition 1st Edition

Languages

Python

Concepts

Deep Learning

Authors (2):

Meysam Ghaffari

Lior Gazit

View More author details

Table of Contents (14) Chapters

Preface

1. Chapter 1: Navigating the NLP Landscape: A Comprehensive Introduction

2. Chapter 2: Mastering Linear Algebra, Probability, and Statistics for Machine Learning and NLP FREE CHAPTER

3. Chapter 3: Unleashing Machine Learning Potentials in Natural Language Processing

4. Chapter 4: Streamlining Text Preprocessing Techniques for Optimal NLP Performance

5. Chapter 5: Empowering Text Classification: Leveraging Traditional Machine Learning Techniques

6. Chapter 6: Text Classification Reimagined: Delving Deep into Deep Learning Language Models

7. Chapter 7: Demystifying Large Language Models: Theory, Design, and Langchain Implementation

8. Chapter 8: Accessing the Power of Large Language Models: Advanced Setup and Integration with RAG

9. Chapter 9: Exploring the Frontiers: Advanced Applications and Innovations Driven by LLMs

10. Chapter 10: Riding the Wave: Analyzing Past, Present, and Future Trends Shaped by LLMs and AI

11. Chapter 11: Exclusive Industry Insights: Perspectives and Predictions from World Class Experts

12. Index

Why subscribe?

13. Other Books You May Enjoy

Setting up an LLM application – local open source models

Now, we shall touch on the complementary approach to a closed source implementation, that is, an open source, local implementation.

We will see how you can achieve a similar functional outcome to the one we reviewed in the previous section, without having to register for an account, pay, or share prompts that contain possibly sensitive information with a third-party vendor, such as OpenAI.

About the different aspects that distinguish between open source and closed source

When selecting between open source LLMs, such as LLaMA and GPT-J, and closed source, API-based models such as OpenAI’s GPT, several critical factors must be considered.

Firstly, cost is a major factor. Open source LLMs often have no licensing fees, but they require significant computational resources for training and inference, which can be expensive. Closed source models, while potentially carrying a subscription or pay-per-use fee...