Quick Guide to ChatGPT, Embeddings, and Other Large Language Models (LLMs)

Quick Guide to ChatGPT, Embeddings, and Other Large Language Models (LLMs)

by Sinan Ozdemir
Released November 2023
Publisher(s): Pearson
ISBN: 0138237085

Watch it now on the O’Reilly learning platform with a 10-day free trial.

O’Reilly members get unlimited access to books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial

Video description

9+ Hours of Video Instruction

Learn how to use and launch large language models (LLMs) like GPT, T5, and BERT at scale with real-world case studies.

Overview:
Quick Guide to ChatGPT, Embeddings, and Other Large Language Models (LLMs) is a quick-start guide to help people use and launch LLMs like GPT, T5, and BERT at scale. It shows a step-by-step approach to building and deploying LLMs, with real-world case studies to illustrate the concepts. The video covers topics such as building recommendation engines with siamese BERT architectures, launching an information retrieval system with OpenAI embeddings and GPT3, and building an image captioning system with the vision transformer and GPT-J. This guide provides clear instructions and best practices for using LLMs. It fills a gap in the market by providing a guide to using LLMs and will be a valuable resource for anyone looking to use LLMs in their projects.

Large language models (LLMs) are a type of artificial intelligence (AI) that use deep learning to process natural language. LLMs are trained on large datasets of text and can be used to generate text, answer questions, and perform other tasks related to natural language processing. LLMs are becoming increasingly popular for a variety of applications, such as recommendation engines, information retrieval systems, image captioning, and translation/summarization pipelines. LLMs are also being used to build chatbots to have conversations that change their style of speaking depending on who they are talking to. LLMs are powerful tools that can help organizations and individuals make sense of large amounts of data and generate insights that would otherwise be difficult to obtain.

Related Learning:

Companion files for this course are available at https://github.com/sinanuozdemir/quick-start-guide-to-llms.

About the Instructor

Sinan Ozdemir is founder and CTO of LoopGenius, where he uses state-of-the-art AI to help people create and run their businesses. He has lectured in data science at Johns Hopkins University and authored multiple books, videos and numerous online courses on data science, machine learning, and generative AI. He also founded the recently acquired Kylie.ai, an enterprise-grade conversational AI platform with RPA capabilities. Sinan most recently published Quick Guide to Large Language Models, and launched a podcast audio series, AI Unveiled. Ozdemir holds a master's degree in pure mathematics from Johns Hopkins University.


Skill Level:

  • Intermediate
  • Advanced

Learn How To:

  • Launch an application using proprietary models with an example of an information retrieval system with OpenAI embeddings and GPT3 for Question/Answering.
  • Fine-tune GPT3 with custom examples using their API to get better results.
  • Learn the basics of prompt engineering with GPT3 to get more nuanced examples by building a chatbot with persona style depending on who they are talking to using the information retrieval system.
  • Deploy custom LLMs to the cloud

Who Should Take This Course:

  • Machine learning engineers with experience in ML, neural networks, and NLP
  • Developers, data scientists, and engineers who are interested in using LLMs for their projects
  • Those who want the best outputs from the GPT-3 or ChatGPT model
  • Those interested in state-of-the-art NLP architecture
  • Those interested in productionizing and fine-tuning LLMs
  • Those comfortable using libraries like Tensorflow or PyTorch
  • Those comfortable with linear algebra and vector/matrix operations

Course Requirements:

  • Python 3 proficiency with some experience working in interactive Python environments including Notebooks (Jupyter/Google Colab/Kaggle Kernels)
  • Comfortable using the Pandas library and either Tensorflow or PyTorch
  • Understanding of ML/deep learning fundamentals including train/test splits, loss/cost functions, and gradient descent

About Pearson Video Training

Pearson publishes expert-led video tutorials covering a wide selection of technology topics designed to teach you the skills you need to succeed. These professional and personal technology videos feature world-leading author instructors published by your trusted technology brands: Addison-Wesley, Cisco Press, Pearson IT Certification, Sams, and Que Topics include: IT Certification, Network Security, Cisco Technology, Programming, Web Development, Mobile Development, and more. Learn more about Pearson Video training at http://www.informit.com/video.

Table of contents

  1. Introduction
    1. Quick Guide to Large Language Models: Introduction
  2. Module 1: Introduction to Large Language Models
    1. Module Introduction
  3. Lesson 1: Overview of Large Language Models
    1. Topics
    2. 1.1 What Are Language Models?
    3. 1.2 Popular Modern LLMs
    4. 1.3 Applications of LLMs
  4. Lesson 2: Semantic Search with LLMs
    1. Topics
    2. 2.1 Introduction to Semantic Search
    3. 2.2 Building a Semantic Search System
    4. 2.3 Optimizing Semantic Search with Cross-Encoders and Fine-Tuning
  5. Lesson 3: First Steps with Prompt Engineering
    1. Topics
    2. 3.1 Introduction to Prompt Engineering
    3. 3.2 Working with Prompts Across Models
    4. 3.3 Building a Retrieval-Augmented Generation Bot with ChatGPT and GPT-4
  6. Module 2: Getting the Most Out of LLMs
    1. Module Introduction
  7. Lesson 4: Optimizing LLMs with Fine-Tuning
    1. Topics
    2. 4.1 Transfer Learning—A Primer
    3. 4.2 The OpenAI Fine-Tuning API
    4. 4.3 Case Study: Predicting with Amazon Reviews–Part 1
    5. 4.4 Case Study: Predicting with Amazon Reviews–Part 2
  8. Lesson 5: Advanced Prompt Engineering
    1. Topics
    2. 5.1 Input/Output Validation
    3. 5.2 Batch Prompting + Prompt Chaining
    4. 5.3 Chain-of-Thought Prompting
    5. 5.4 Preventing Prompt Injection Attacks
    6. 5.5 Assessing an LLM's Encoded Knowledge Level
  9. Lesson 6: Customizing Embeddings + Model Architectures
    1. Topics
    2. 6.1 Case Study—Building an Anime Recommendation System
    3. 6.2 Using OpenAI’s Embedding Models
    4. 6.3 Fine-Tuning an Embedding Model to Capture User Behavior
  10. Module 3: Advanced LLM Usage
    1. Module Introduction
  11. Lesson 7: Moving Beyond Foundation Models
    1. Topics
    2. 7.1 The Vision Transformer
    3. 7.2 Using Cross Attention to Mix Data Modalities
    4. 7.3 Case Study—Visual QA: Setting Up Our Model
    5. 7.4 Case Study—Visual QA: Setting Up Our Parameters and Data
    6. 7.5 Introduction to Reinforcement Learning from Feedback
    7. 7.6 Aligning FLAN-T5 with Reinforcement Learning from Feedback
  12. Lesson 8: Advanced Open-source LLM Fine-Tuning
    1. Topics
    2. 8.1 BERT for Multi-label Classification–Part 1
    3. 8.2 BERT for Multi-label Classification–Part 2
    4. 8.3 Writing LaTeX with GPT-2
    5. 8.4 Case Study: Sinan’s Attempt at Wise Yet Engaging Responses – SAWYER
    6. 8.5 Instruction Alignment of LLMs: Supervised Fine-Tuning
    7. 8.6 Instruction Alignment of LLMs: Reward Modeling
    8. 8.7 Instruction Alignment of LLMs: RLHF
    9. 8.8 Instruction Alignment of LLMs: Using Our Instruction Aligned LLM
  13. Lesson 9: Moving LLMs into Production
    1. Topics
    2. 9.1 Cost Projecting and Deploying LLMs to Production
    3. 9.2 Knowledge Distillation
  14. Summary
    1. Quick Guide to Large Language Models: Summary

Product information

  • Title: Quick Guide to ChatGPT, Embeddings, and Other Large Language Models (LLMs)
  • Author(s): Sinan Ozdemir
  • Release date: November 2023
  • Publisher(s): Pearson
  • ISBN: 0138237085