Generative AI and Large Language Models
Keep adding new skills with 10,000+ programs for $239 (usually $399). Save now.
Generative AI and Large Language Models
This course is part of multiple programs.
4,778 already enrolled
Included with
Ask Coursera
12 reviews
Recommended experience
12 reviews
Recommended experience
Skills you'll gain
Details to know
See how employees at top companies are mastering in-demand skills
Build your subject-matter expertise
- Learn new concepts from industry experts
- Gain a foundational understanding of a subject or tool
- Develop job-relevant skills with hands-on projects
- Earn a shareable career certificate
There are 5 modules in this course
Welcome to the world of Generative AI and Large Language Models (LLMs)—where technology mirrors human creativity and intelligence. This course is designed to provide you with a comprehensive understanding of generative models, including their evolution, applications, and the underlying architectures that make them possible.
Throughout the modules, you'll explore various generative techniques such as GANs (Generative Adversarial Networks), VAEs (Variational Autoencoders), diffusion models, and multimodal AI. You'll also gain hands-on experience with tools like OpenAI's GPT, Hugging Face, Streamlit, and MLflow, ensuring you can deploy and fine-tune models for real-world applications.
Take your first steps into the exciting world of generative AI, where you'll distinguish between various model types including GANs, VAEs, transformers, and diffusion models. You'll explore the evolution of generative technologies and examine their real-world applications while considering important ethical implications that accompany these powerful tools.
What's included
9 videos7 readings5 assignments2 ungraded labs
9 videos•Total 21 minutes
- Welcome to Generative AI•2 minutes
- Training a Discriminative Model: Logistic Regression on 2D Blobs•2 minutes
- Fitting and Visualizing a Generative Model•2 minutes
- From GANs to Autoregressive Models: Hands-On with Generative Basics•3 minutes
- Diffusion Models in Action: From Noise to Realistic Outputs•2 minutes
- What Can LLMs Do Today? Real Use Cases Across Providers•2 minutes
- What Can Vision-Language Models Do? Image + Text in Action•3 minutes
- Uncovering Bias in LLM Outputs•2 minutes
- Hallucinations & Misinformation in Action•2 minutes
7 readings•Total 63 minutes
- Foundations of Generative AI•8 minutes
- Types and Use Cases of Generative AI•8 minutes
- Foundations of Generative Modeling: From GANs to VAEs•10 minutes
- From Autoregressive to Diffusion: How Modern Generative Models Took Over•10 minutes
- Understanding Large Language Models (LLMs): Capabilities, Providers, and Trends•10 minutes
- Understanding Vision-Language Models (VLMs): Capabilities, Use Cases, and Trends•10 minutes
- Responsible AI: Risks and Mitigation Strategies•7 minutes
5 assignments•Total 90 minutes
- Foundations of Generative AI•30 minutes
- Knowledge Check - What is Generative AI?•15 minutes
- Knowledge Check - Generative Model Evolution•15 minutes
- Knowledge Check - LLMs & VLMs•15 minutes
- Knowledge Check - Ethical AI Deployment•15 minutes
2 ungraded labs•Total 105 minutes
- Sample from a Simple Generative Model•45 minutes
- Sample from a VAE and an Autoregressive Model•60 minutes
Explore the revolutionary transformer architecture that powers today's most advanced language models. You'll gain hands-on experience with self-attention mechanisms, learn how transformers process and generate text, and experiment with fine-tuning using Hugging Face Transformers. This module bridges theory with practical implementation, equipping you with skills to work directly with cutting-edge LLM technology.
What's included
7 videos6 readings4 assignments3 ungraded labs
7 videos•Total 16 minutes
- Transformers Made LLMs Possible: Here's Why That Matters•2 minutes
- The Problem with RNNs and How Transformers Fix It•4 minutes
- Self-Attention, Multi-Head Attention, and Feedforward Networks•3 minutes
- Tuning LLM Output with Temperature, Top-k, and Top-p•2 minutes
- Accessing LLMs Through APIs and UIs•1 minute
- Prompt Engineering: Small Tweaks, Big Results•2 minutes
- Fine-Tuning a Transformer with Hugging Face•2 minutes
6 readings•Total 43 minutes
- From RNNs to Transformers: A New Way to Process Sequences•8 minutes
- Anatomy of Transformers and Their Architectures•4 minutes
- Prompt Engineering Essentials: How to Write Better Prompts•10 minutes
- Calling LLMs via API: How to Get Started Safely and Effectively•8 minutes
- LLM Fine-Tuning Strategies: From Supervised to Aligned•7 minutes
- Understanding PEFT and Reinforcement Learning Fine-Tuning•6 minutes
4 assignments•Total 75 minutes
- Working with Transformers and Fine-Tuning •30 minutes
- Knowledge Check - Transformer Foundations•15 minutes
- Knowledge Check - Prompt Engineering & APIs•15 minutes
- Knowledge Check - LLM Fine-Tuning•15 minutes
3 ungraded labs•Total 160 minutes
- Experiment with LLM Sampling Parameters•40 minutes
- Prompt and Compare Across LLMs•60 minutes
- Perform Lightweight Fine-Tuning with LoRA•60 minutes
Take your LLM knowledge to the next level with practical applications that power modern AI systems. You'll implement retrieval-augmented generation to enhance responses with external knowledge, use structured output techniques for consistent formatting, and deploy models through APIs. This module tackles both the theory and practice behind modern LLM applications, showing you how to build real-world applications with today's most advanced language models.
What's included
5 videos4 readings5 assignments3 ungraded labs
5 videos•Total 8 minutes
- Retrieving Knowledge: Embeddings and Vector Search with FAISS•1 minute
- Grounded Generation: Adding Retrieval to an LLM Pipeline•1 minute
- Prompting LLMs for Structured Output and Function Simulation•2 minutes
- Deploying an LLM Using MLflow and Streamlit Cloud•1 minute
- Simulate an AI Agent Using OpenAI Function Calling or Tool Simulation•1 minute
4 readings•Total 37 minutes
- What is RAG and Why Does It Matter?•10 minutes
- Designing for Structure: Output Formats and Tool Use•10 minutes
- LLM Deployment: Options, Challenges, and Best Practices•10 minutes
- AI Agents 101: Key Concepts and Applications•7 minutes
5 assignments•Total 90 minutes
- Hands-on Applications of LLMs•30 minutes
- Knowledge Check - Retrieval-Augmented Generation•15 minutes
- Knowledge Check - Structured Output & Function Calls•15 minutes
- Knowledge Check - LLM Deployment•15 minutes
- Knowledge Check - AI Agents•15 minutes
3 ungraded labs•Total 165 minutes
- Implement a Simple RAG Pipeline with FAISS and Hugging Face•60 minutes
- Prompt LLMs for Structured Output + Simulated Function Use•45 minutes
- Deploy a Text Generation Model with Streamlit + MLflow•60 minutes
Discover the technology behind today's most impressive image generation systems. You'll learn how diffusion models gradually transform random noise into stunning visuals through an iterative denoising process. Through practical coding exercises, you'll implement your own diffusion model using PyTorch, explore Stable Diffusion for text-to-image generation, and compare diffusion with earlier approaches like GANs and VAEs to understand why diffusion has become the dominant paradigm in visual generation.
What's included
4 videos4 readings4 assignments3 ungraded labs
4 videos•Total 10 minutes
- Why Diffusion Has Become the Preferred Approach for High-Quality Image Generation•3 minutes
- Text-to-Image Generation with Stable Diffusion•1 minute
- Exploring Latent Space in Diffusion Models•1 minute
- GANs vs. VAEs vs. Diffusion: What Do the Outputs Say?•5 minutes
4 readings•Total 27 minutes
- Your First Tiny Diffusion Model: Simulate Diffusion in Pixel Space•6 minutes
- The Diffusion Process Explained•7 minutes
- Inside Stable Diffusion: Architecture and Prompt Control•7 minutes
- Choosing the Right Generative Model: A Comparative Guide•7 minutes
4 assignments•Total 75 minutes
- Diffusion and Generative Model Comparison•30 minutes
- Knowledge Check - Diffusion Basics•15 minutes
- Knowledge Check - Training with Stable Diffusion•15 minutes
- Knowledge Check - Comparing Models•15 minutes
3 ungraded labs•Total 165 minutes
- Simulate Forward Diffusion on Images Using PyTorch•45 minutes
- Generate Custom Images with Stable Diffusion•60 minutes
- Compare Outputs from GAN, VAE, and Diffusion Models•60 minutes
Discover how cutting-edge AI models can integrate text, images, and audio to create truly multimodal experiences. You'll investigate vision-language models like CLIP and BLIP that understand relationships between text and images, implement audio-based AI with Whisper for speech recognition, and gain hands-on experience building systems that can process multiple types of data simultaneously. This module prepares you for the increasingly multimodal future of generative AI where models seamlessly combine different kinds of information.
What's included
6 videos4 readings4 assignments1 programming assignment3 ungraded labs
6 videos•Total 9 minutes
- From Text to Everything: The Multimodal Revolution•2 minutes
- How Do Multimodal Models Combine Text, Image, and Audio?•1 minute
- Generating Captions with BLIP•1 minute
- Zero-Shot Image Classification with CLIP•1 minute
- Transcribing Speech to Text with Whisper•1 minute
- Generating Speech from Text with TTS•1 minute
4 readings•Total 40 minutes
- Multimodal Generative AI: A Foundation•10 minutes
- Understanding VLMs: CLIP, BLIP, Gemini•7 minutes
- Understanding Whisper and Audio-Based Generative AI•7 minutes
- Designing Your Own Generative AI Assistant: From Learner to Builder•16 minutes
4 assignments•Total 75 minutes
- Multimodal Generative AI•30 minutes
- Knowledge Check - Multimodal Foundations•15 minutes
- Knowledge Check - CLIP, BLIP, and Gemini•15 minutes
- Knowledge Check - Audio-Based Models•15 minutes
1 programming assignment•Total 120 minutes
- Capstone Project - Build Your Own Generative AI Assistant with RAG, LLMs, and Multimodal Input•120 minutes
3 ungraded labs•Total 150 minutes
- Explore Cross-Modal Embeddings with CLIP•45 minutes
- Image Captioning and Classification with VLMs•45 minutes
- Transcribe and Generate Audio with Whisper + TTS•60 minutes
Earn a career certificate
Add this credential to your LinkedIn profile, resume, or CV. Share it on social media and in your performance review.
Instructor
Why people choose Coursera for their career
Frequently asked questions
To access the course materials, assignments and to earn a Certificate, you will need to purchase the Certificate experience when you enroll in a course. You can try a Free Trial instead, or apply for Financial Aid. The course may offer 'Full Course, No Certificate' instead. This option lets you see all course materials, submit required assessments, and get a final grade. This also means that you will not be able to purchase a Certificate experience.
When you enroll in the course, you get access to all of the courses in the Certificate, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile.
More questions
Financial aid available,