Large Language Models and ChatGPT in 3 Weeks
Published by Pearson
Use Claude, ChatGPT, DeepSeek & more to unlock AI value and drive real impact
- Hands-on HuggingFace, ChatGPT, Llama and Claude experience: Gain practical experience using LLMs to create custom prompts and generate actionable results.
- Non-coder and data-focused friendly: Designed for individuals without a coding or data science background, this class is tailored to ensure easy comprehension.
- Comprehensive LLM, DeepSeek, Claude and GPT coverage: From basics to advanced topics like prompt engineering and cost projection to advanced topics like agents, RAG, and Multimodality, this course covers everything needed to apply these technologies to different use cases.
Are you curious how natural language processing (NLP) technology and LLMs can benefit your business and automate all kinds of tasks, enhance chatbot intelligence, and extract new insights from your data? These sessions will delve into the potential of LLMs and provide guidance on how you can begin using them.
This is a 3-week, comprehensive course designed to teach non-coders and data-focused professionals how to leverage the latest advancements in natural language processing using technologies like ChatGPT and Claude. Over the course of several weeks, participants will learn how to extract actionable insights, optimize business operations, and streamline workflows, all with the help of large language models.
During Week 1, participants will be introduced to the basics of large language models like GPT, and prompt engineering. This week will provide participants with a fundamental understanding of how these technologies work and what they can do.
Week 2 will focus on getting actionable results and cost projecting using LLMs. Participants will learn how to use AI to identify patterns and make predictions as well as how to calculate the costs associated with using them.
Finally, during Week 3, participants will learn how to build viable prototypes with LLMs and GPT. This week will focus on putting theory into practice by providing participants with hands-on experience using GPT-4 to create custom prompts, agents, RAG systems, and more.
What you’ll learn and how you can apply it
- Large Language Models (LLMs) and the Generative Pre-trained Transformers (GPT) family of models
- Techniques for prompt engineering and getting actionable results with LLMs
- The costs associated with using LLMs and GPT, and how to project these costs
- How to build viable prototypes with ChatGPT, Claude and other LLMs
- How to navigate novel LLMs and how they might fit into existing infrastructure
- How applications like RAG and agents work under the hood and how to optimize their performance
And you’ll be able to:
- Create custom prompts and generate text using ChatGPT and other LLMs
- Identify patterns, make predictions, and extract actionable insights from large amounts of unstructured data
- Calculate the costs associated with using LLMs for various applications and use cases
- Build viable prototypes and models using LLMs that can be integrated into different workflows and business operations
This live event is for you because...
- Non-coding or data-focused professionals
- Those interested in learning the fundamentals of LLMs and natural language processing
- Individuals without a coding or data science background
- Beginners and more advanced learners
Prerequisites
Attendees of this class do not necessarily need prior coding or data science experience, as the course is designed for non-coding or data-focused professionals. However, some basic familiarity with natural language processing (NLP) concepts would be helpful. Attendees should have a basic understanding of how NLP techniques like text analysis and sentiment analysis work, as well as some familiarity with machine learning concepts like supervised and unsupervised learning.
In addition, attendees should have a general understanding of how businesses and organizations operate and be familiar with the types of problems that LLMs can help solve. A willingness to learn and a curiosity about the potential applications of LLMs are also important.
Course Set-up
- Course github repository with the PDFs of slides, plus code and links in a Jupyter notebook
Recommended Preparation
- Read: Chapter 1, Quick Start Guide to Large Language Models: Strategies and Best Practices for using ChatGPT and Other LLMs by Sinan Ozdemir.
- Watch: AI Catalyst Conference: NLP with ChatGPT (and other Large Language Models) by Jon Krohn.
Recommended Follow-up
- Watch: Introduction to Transformer Models for NLP
- Watch: Quick Guide to ChatGPT, Embeddings, and Other Large Language Models (LLMs) by Sinan Ozdemir
- Audio: AI Unveiled (Audio) by Sinan Ozdemir
Schedule
The time frames are only estimates and may vary according to how the class is progressing.
Week 1: Introduction to LLMs, GPT, and Prompt Engineering
Session 1: Large Language Models (LLMs) and Generative Pre-trained Transformers (GPT) (60 minutes)
- Introduction to LLMs and the landscape of Modern AI with HuggingFace
- Introduction to BERT Llama, ChatGPT, GPT-4, Claude, and more
- Understanding how LLMs work
- Breaking down the mechanisms that makes these architectures so powerful
- Using LLMs like GPT and Claude in the web and using the API
- Q&A (5 mins)
- Break (15 minutes)
Session 2: Prompt Engineering (60 minutes)
- Defining prompt engineering
- Introduction to prompting
- Hands on prompting examples + prompt versioning
- Prompt chaining, chain of thought prompting, and few-shot learning
- Q&A (5 mins)
- Q&A (5 mins)
- Break (15 minutes)
Session 3: Text Generation with LLMs (60 minutes)
- Understanding how LLMs generate text
- Generating text with ChatGPT and T5
- Introduction to Week 1 Assignment (5 minutes)
- Q&A (5 mins)
Week 2: Getting Actionable Results and Cost Projecting with LLMs and GPT
Session 1: Identifying Patterns and Making Predictions (60 minutes)
- Using LLMs to identify patterns and make predictions
- Analyzing large amounts of unstructured data + fine-tuning
- Applications of LLMs for prediction modeling + time-series analysis
- Q&A (5 mins)
- Break (15 minutes)
Session 2: Cost Projecting with LLMs and GPT (60 minutes)
- Understanding the costs associated with using LLMs and GPT
- How to project costs for various use cases
- ROI calculation
- Q&A (5 mins)
- Break (15 minutes)
Session 3: Use Case Discussion (60 minutes)
- Examples of LLMs and GPT applications in different industries
- Introduction to Agents, RAG, and Multimodality
- Introduction to Week 2 Assignment (5 minutes)
- Q&A (5 mins)
Week 3: Building Viable Prototypes with LLMs
Session 1: Building Prototypes with LLMs (60 minutes)
- Hands-on experience building viable prototypes with LLMs
- Creating custom dynamic prompts and generating text
- Examples of building RAG, GraphRAG, and Agents
- Q&A (5 mins)
- Break (15 minutes)
Session 2: Model Evaluation (60 minutes)
- Understanding how to evaluate LLM models
- Identifying areas for improvement with AI drift analysis
- Techniques for collecting labeled data and fine-tuning models
- Q&A (5 mins)
- Break (15 minutes)
Session 3: Integration with Different Workflows (60 minutes)
- How to integrate LLMs and Multimodal AI into different workflows and business operations
- Best practices for implementation for agent and RAG applications
- Future applications of LLMs
- Introduction to Week 3 Assignment (5 minutes)
- Q&A (5 mins)
Wrap-up and Final Q&A (30 minutes)
Your Instructor
Sinan Ozdemir
Sinan Ozdemir is the founder of Crucible, an AI factory platform that helps teams convert existing workflows into custom models. He is a Y Combinator alum, AI & LLM Advisor at Tola Capital, and the author of multiple books on data science and machine learning including Building Agentic AI, Quick Start Guide to LLMs, and Principles of Data Science. Sinan is a former lecturer of data science at Johns Hopkins University and the founder of Kylie.ai, an enterprise-grade conversational AI platform (acquired 2014). He holds a master's degree in pure mathematics from Johns Hopkins University and is based in San Francisco, California.