Online Course
Intro to LLMs

Name: Intro to Large Language Models Course (LLMs)—Enroll Now
Price: 36 USD

with Lauren Newbould

Start your AI Engineer career journey: Master Transformer Architecture and the Essentials of Modern AI

4.8

863 reviews on

Start for free

6,133 students already enrolled

Skill level:

Intermediate

Duration:

3 hours

Lessons (3 hours)

CPE credits:

4

CPE stands for Continuing Professional Education and represents the mandatory credits a wide range of professionals must earn to maintain their licenses and stay current with regulations and best practices. One CPE credit typically equals 50 minutes of learning. For more details, visit NASBA's official website: www.nasbaregistry.org

Accredited

certificate

What you learn

Create AI-driven applications for specific business needs.
Boost your career by mastering AI engineering skills.
Understand key LLM concepts like attention and self-attention.
Integrate OpenAI’s API to connect products with AI models.
Gain an introduction to LangChain and Hugging Face.

Topics & tools

AITransformersLLMsAttentionGPTLangchainBERTHuggingfaceXLNetNatural Language ProcessingPython

Your instructor

Lauren Newbould

Senior Data Scientist | Professional Development Expert

Track record

Bringing real-world expertise from leading global companies

Academic background

Master's degree, Social Research Methods & Statistics

Media and recognition

Speaker on NLP for social good in developing countries
Advocate for ethical and open data science
Contributor to AI accessibility initiatives

Ask Lauren a question

Course overview

Accredited certificates

Course OVERVIEW

Description

CPE Credits: 4 Field of Study: Information Technology
Delivery Method: QAS Self Study

In recent years, large language models (LLMs) have dominated the tech news for their incredible ability to write poetry, essays, social media content, code, and more. They’re the hot new topic in natural language processing. This Intro to Large Language Models course teaches you the knowledge and skills required to experiment and create your own language model solutions. Through a combination of video lessons and practical coding exercises, we’ll cover what these language models are, their functions, and ways to implement them into your own projects. Whether you want to generate content, create a chatbot, or train these models on your own custom data and NLP tasks, this course equips you with the fundamental tools and concepts to fine-tune LLM models and tackle these challenges.

Prerequisites

Python (version 3.8 or later), Hugging Face Transformers library, and a code editor or IDE (e.g., VS Code or Jupyter Notebook)
Basic understanding of Python programming is required.
No prior experience with natural language processing or machine learning is necessary.

Advanced preparation

Curriculum

46 lessons 19 exercises 1 exam

1. Introduction to Large Language Models

16 min

We’ll begin our journey with an introduction into large language models., We’ll study the world of LLMs, their applications, training processes, and what datasets they’ve been trained on.

16 min

We’ll begin our journey with an introduction into large language models., We’ll study the world of LLMs, their applications, training processes, and what datasets they’ve been trained on.

Introduction to the course Free

Course Materials and Notebooks Free

What are LLMs? Free

How large is an LLM? Free

General purpose models Free

Pre-training and fine tuning Free

Exercise Free

What can LLMs be used for? Free
2. The Transformer Architecture

24 min

In this segment of the LLM course, we’ll break down the transformers' architecture and explain the mechanics behind encoders and decoders, embeddings, multi-headed attention, and the significance of a feed-forward layer. You’ll learn the advantages of transformers over RNNs.

24 min

In this segment of the LLM course, we’ll break down the transformers' architecture and explain the mechanics behind encoders and decoders, embeddings, multi-headed attention, and the significance of a feed-forward layer. You’ll learn the advantages of transformers over RNNs.

Deep learning recap Free

Exercise

The problem with RNNs Free

The solution: attention is all you need Free

Exercise

The transformer architecture

Exercise

Input embeddings

Exercise

Multi-headed attention

Exercise

Feed-forward layer

Masked multihead attention

Exercise

Predicting the final outputs
3. Getting started with GPT models

33 min

We’ll examine GPT models closely and begin our practical part of the LLM tutorial. We’ll connect to OpenAI’s API and implement a simple chatbot with a personality: a poetic chatbot. I’ll also show you how to use LangChain to work with your own custom data, feeding information from the 365 web pages to our model.

33 min

We’ll examine GPT models closely and begin our practical part of the LLM tutorial. We’ll connect to OpenAI’s API and implement a simple chatbot with a personality: a poetic chatbot. I’ll also show you how to use LangChain to work with your own custom data, feeding information from the 365 web pages to our model.

What does GPT mean?

The development of ChatGPT

Importamt Update

OpenAI API

Generating text

Customizing GPT Output

Key word text summarization

Exercise

Coding a simple chatbot

Introduction to Langchain in Python

Langchain

Exercise

Adding custom data to our chatbot
4. Hugging Face Transformers

27 min

The Hugging Face package is an open-source package, which allows us an alternative way to interact with LLMs. We’ll learn about pre-trained and customized tokenizers and how to integrate Hugging Face into Pytorch and Tensorflow deep learning workflows.

27 min

The Hugging Face package is an open-source package, which allows us an alternative way to interact with LLMs. We’ll learn about pre-trained and customized tokenizers and how to integrate Hugging Face into Pytorch and Tensorflow deep learning workflows.

Hugging Face package

Exercise

The transformer pipeline

Pre-trained tokenizers

Special tokens

Exercise

Hugging Face and PyTorch, TensorFlow

Saving and loading models
5. Question and answer models with BERT

32 min

This section of our Intro to Large Language Models course will explore BERT's architecture and contrast it with GPT models. It will delve into the workings of question-answering systems both theoretically and practically and examine variations of BERT—including the optimized RoBERTa and the smaller lightweight version DistilBERT.

32 min

This section of our Intro to Large Language Models course will explore BERT's architecture and contrast it with GPT models. It will delve into the workings of question-answering systems both theoretically and practically and examine variations of BERT—including the optimized RoBERTa and the smaller lightweight version DistilBERT.

GPT vs BERT

Exercise

BERT architecture

Exercise

Loading the model and tokenizer

BERT embeddings

Calculating the response

Creating a QA bot

BERT, RoBERTa, DistilBERT

Exercise
6. Text classification with XLNet

26 min

In the final Intro to Large Language Models course section, we’ll look under the hood of XLNET (a novel LLM), that uses permutations of data sets to train a model. We’ll also compare XLNet and our previously discussed models, BERT and GPT.

26 min

In the final Intro to Large Language Models course section, we’ll look under the hood of XLNET (a novel LLM), that uses permutations of data sets to train a model. We’ll also compare XLNet and our previously discussed models, BERT and GPT.

GPT vs BERT vs XLNET

Exercise

A note on the following lecture

Preprocessing our data

XLNet Embeddings

Fine tuning XLNet

Evaluating our model
7. Course exam

30 min

30 min

Course exam

Free lessons

1.1 Introduction to the course

2 min

1.2 Course Materials and Notebooks

1 min

1.3 What are LLMs?

3 min

1.4 How large is an LLM?

3 min

1.5 General purpose models

1 min

1.6 Pre-training and fine tuning

3 min

Start for free

I’ve been with 365 Data Science for about two years, starting with the Business Analyst course and now working on Data Engineering. My Excel skills improved so much they helped me land two promotions, and my coding knowledge—especially in Python—has grown dramatically. The courses go deeper, helping me understand the mechanisms behind technology. With a set schedule and commitment, the results are real. I highly recommend 365 and look forward to continuing my learning journey.

Mattew M.

Before 365: Mortgage Loan Officer | Movement Mortgage

After 365: Compliance Analyst | Movement Mortgage

See all reviews

96%

of our students recommend

365 Data Science.

Early in my career, I took 365 Data Science courses that built a strong foundation in data science and financial analysis with Excel. The detailed, visual content—from basics to advanced—helped me grasp key concepts, develop practical skills, and apply them to real projects in multiple industries. The instructors, quick responses to questions, and collaborative community made learning even more engaging. 365 truly supports continuous growth, and I recommend it to anyone starting or advancing in data and AI.