Quick Start Guide to Large Language Models (LLMs): ChatGPT, Llama, Embeddings, Fine-Tuning, and Multimodal AI, 2nd Edition

The Sneak Peek program provides early access to Pearson video products and is exclusively available to subscribers. Content for titles in this program is made available throughout the development cycle, so products may not be complete, edited, or finalized, including video post-production editing.

Introduction

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

Module 1: Introduction to Large Language Models

Module Introduction

Lesson 1: Overview of Large Language Models

Topics
1.1 What Are Large Language Models?
1.2 Popular Modern LLMs
1.3 Applications of LLMs

Lesson 2: Semantic Search with LLMs

Topics
2.1 Introduction to Semantic Search
2.2 Building a Semantic Search System
2.3 Optimizing Semantic Search with Cross-Encoders and Fine-Tuning

Lesson 3: First Steps with Prompt Engineering

Topics
3.1 Introduction to Prompt Engineering
3.2 Working with Prompts Across Models
3.3 Building a Retrieval-Augmented Generation BOT with ChatGPT and GPT-4

Lesson 4: Retrieval Augmented Generation + AI Agents

Topics
4.1 Introduction to Retrival Augmented Generation (RAG)
4.2 Building a RAG bot
4.3 Using Open Source Models with RAG
4.4 Expanding into AI Agents

Module 2: Getting the Most Out of LLMs

Module Introduction

Lesson 5: Optimizing LLMs with Fine-Tuning

Topics
5.1 Transfer Learning-A Primer
5.2 The OpenAI Fine-Tuning API
Lesson 6: Advanced Prompt Engineering

Topics
6.1 Input/Output Validation
6.2 Batch Prompting + Prompt Chaining
6.3 Chain-of-Thought Prompting
6.4 Preventing Prompt Injection Attacks
6.5 Assessing an LLM’s Encoded Knowledge Level

Lesson 7: Customizing Embeddings + Model Architectures

Topics
7.1 Case Study: Building an Anime Recommendation System
7.2 Using OpenAI’s Embedded Models
7.3 Fine-tuning an Embedding Model to Capture User Behavior

Lesson 8: AI Alignment-First Principles

Topics
8.1 Introduction to AI Alignment
8.2 Evaluating Alignment Plus Ethics

Module 3: Advanced LLM Usage

Lesson 9: Moving Beyond Foundation Models

Topics
9.1 The Vision Transformer
9.2 Using Cross Attention to Mix Data Modalities
9.3 Case Study-Visual QA: Setting Up Our Model
9.4 Case Study-Visual QA: Setting Up Our Parameters and Data
9.5 Introduction to Reinforcement Learning from Feedback
9.6 Aligning FLAN-T5 with Reinforcement Learning from Feedback

Lesson 10: Advanced Open-Source LLM Fine-Tuning

Topics
10.3 Writing LaTeX with GPT-2
10.4 Case Study: Sinan’s Attempt at Wise Yet Engaging Responses-Sawyer
10.5 Instruction Alignment of LLMs: Supervised Fine-Tuning
10.6 Instruction Alignment of LLMs: Reward Modeling
10.7 Instruction Alignment of LLMs: RLHF
10.8 Instruction Alignment of LLMs: Using Our Instruction-Aligned LLM

Lesson 11: Moving LLMs into Production

Topics
11.1 Cost Projecting and Deploying LLMs to Production
11.2 Knowledge Distillation

Lesson 12: LLM Evaluations

Topics
12.3 Evaluating Understanding Tasks
12.4 Probing LLMs for world model

Summary

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