Generative AI, a branch of artificial intelligence, is capable of generating images, text, sounds, music, and videos. It’s widely applied in various professions and industries, and it’s generating significant interest.
If you’re interested in learning about Generative AI and possibly creating your own AI applications, you’ve come to the right place.
We’ve gathered some of the free courses and resources to help you kickstart your journey into Generative AI. Whether you’re a complete beginner or a seasoned AI enthusiast, our guide will lead you in the right direction.
Let’s jump in and explore Generative AI together!
Full Stack LLM Bootcamp
Full Stack LLM Bootcamp provides a two-day program that focuses on emerging best practices and the latest research results to help you confidently transition to building applications with Large Language Models (LLMs).
The program was initially an in-person boot camp in San Francisco in April 2023, and now the recorded lectures are available for free. The course is described as an excellent starting point for anyone interested in Large Language Models and their practical applications.
Prerequisites
These lectures are for Python programmers looking to use Large Language Models (LLMs) in their applications. Having some experience in machine learning, frontend, or backend development is a plus.
Course Inclusion
- Introduction to Large Language Models (LLMs)
- Prompt engineering and creative use of LLMs
- Deployment and operational considerations
- Building user-friendly language interfaces
- Augmenting language models for specific tasks
- Rapid development and deployment of LLM applications
- Future trends and developments in the field
- Foundational concepts of LLMs
Full Stack Deep Learning’s program is an excellent starting point for anyone interested in Large Language Models and their practical applications. With a team of experienced instructors, including UC Berkeley PhD alumni, this resource offers a comprehensive introduction to Generative AI.
Introduction to Generative AI Learning Path
Google Cloud offers a comprehensive Generative AI learning path that covers various aspects of Generative AI, from the basics of large language models to the principles of responsible AI. This learning path is an excellent starting point for anyone looking to gain insights into the world of Generative AI.
Prerequisites
The courses within this learning path are introductory and do not require any specific prerequisites. They are suitable for beginners and anyone interested in learning about Generative AI.
Course Inclusion
- Fundamentals of Generative AI
- Understanding Large Language Models
- Enhancing LLM Performance with Prompt Tuning
- Introduction to Responsible AI
- Google’s Implementation of Responsible AI
- Generative AI Fundamentals
- Responsible AI with Google Cloud
- Applying AI Principles Responsibly
By passing the final quiz, you demonstrate your understanding of foundational concepts in Generative AI.
Whether you’re new to the field or looking to expand your knowledge, these courses provide a solid foundation in Generative AI concepts, large language models, and responsible AI principles.
Microsoft Azure AI Fundamentals: Generative AI
Microsoft Azure offers a comprehensive learning path on Generative AI, focusing on how models are trained to generate new, original content based on natural language input. Generative AI allows for the creation of text, images, or even code output in response to everyday language descriptions.
This learning path is designed to help you get started with Generative AI and explores various aspects, including Azure’s role in providing access to generative AI technology.
Prerequisites
Familiarity with Azure and the Azure portal is recommended as a prerequisite for this learning path. It is suitable for beginners and individuals at various levels, including AI engineers, developers, solution architects, and students.
Course Inclusion
- Introduction to Generative AI
- Natural Language Generation
- Image and Code Generation
- Understanding Large Language Models (LLMs)
- Transformation Models
- Tokenization and Embedding
- Fundamentals of Azure OpenAI Service
- Introduction and Examples of Copilot
- Improve generative AI responses with prompt engineering
Microsoft Azure’s “Generative AI” learning path is an excellent resource for those looking to explore Generative AI in the context of the Azure ecosystem.
With a focus on responsible AI and practical applications, this learning path equips learners with the knowledge and skills required to understand and work with Generative AI.
How Diffusion Models Work
This course, titled “How Diffusion Models Work,” provides an in-depth understanding of diffusion models used in generative AI. It goes beyond simply using pre-built models or APIs and teaches you how to build a diffusion model from scratch.
The course is designed to help you gain hands-on experience with diffusion-based generative AI. The course is taught by Sharon Zhou, the Co-Founder and CEO of Lamini, ensuring you learn from an experienced industry professional.
Prerequisites
This is an intermediate-level course, and having prior knowledge of Python, Tensorflow, or Pytorch will be beneficial to get the most out of the content.
Course Inclusion
- Introduction to Diffusion Models
- The intuition behind Diffusion Models
- Sampling in Diffusion Models
- Neural Networks in Diffusion Models
- Training Diffusion Models
- Controlling Diffusion Models
- Speeding up Diffusion Models
If you’re looking to dive deeper into the world of diffusion models in generative AI, “How Diffusion Models Work” is an ideal resource. This course allows you to build, train, and optimize diffusion models, giving you the practical skills needed to explore this exciting field further.
With free access for a limited time, it’s a great opportunity to expand your generative AI capabilities.
Use the OpenAI API to Code 5 Projects
This course is a comprehensive dive into the world of the OpenAI API. It teaches you how to utilize the OpenAI API to create five exciting projects, including a ChatGPT clone, a DALL-E Image Creator, and an SQL Generator.
These projects explore the diverse capabilities and potential applications of the OpenAI API.
Prerequisites
The course doesn’t specify any prerequisites, but it’s recommended to have a basic understanding of programming languages such as JavaScript, React, Node.js, and TypeScript and familiarity with using APIs in software development.
Course Inclusion
- Introduction, Prerequisites, and Setup
- API Access, Key Management and Authentication
- Understanding Different Models
- Text Completions, Custom Prompts, and Instructions
- Prompt Optimization Techniques
- Building Chatbots with GPT-3
- Image Generation Project 1 | JavaScript
- Image Generation with DALL-E
- Image Generation Project 2 | React Node.js OpenAI NPM Library
- SQL Generator Project | TypeScript Node.js OpenAI NPM Library
If you’re eager to explore the capabilities of the OpenAI API and create exciting projects, this course is an excellent resource. Whether you’re interested in developing ChatGPT applications, generating images with DALL-E, or creating SQL queries, this course has you covered.
The step-by-step guidance and practical projects will enable you to unlock the potential of the OpenAI API.
Create a Large Language Model from Scratch with Python
This course provides an in-depth tutorial on how to create your own large language model from scratch using Python. It delves into data handling, mathematical concepts, and the implementation of transformers behind large language models.
You will explore various topics related to building your language model.
Prerequisites
You need to be familiar with the Python programming language as the course primarily uses Python for coding. It’s beneficial to know about deep learning, especially with respect to neural networks and their training.
Course Inclusion
- Introduction and Setup
- Text Preprocessing
- Linear Algebra Fundamentals
- Data Preparation and Model Inputs
- Switching from CPU to CUDA
- Introduction to PyTorch
- Dot Product and Matrix Multiplication
- Matmul Implementation
- Building a Neural Network
- Building a GPT Model
- Optimizers and Normalization
- Transformer Blocks and Multi-Head Attention
- Model Training and Hyperparameters
- Training on OpenWebText
- Handling Error, Model Saving and Loading
- Scripting and Command-Line Tools
- Pretraining Vs Finetuning
If you are interested in understanding the details of building a large language model from the ground up, this tutorial is a valuable resource.
The course takes you through a step-by-step journey, providing you with the knowledge and skills to create your own language model.
Introduction to Large Language Models with Google Cloud
This introductory course, offered by Google Cloud, is a micro-learning experience that provides an overview of large language models (LLM). It covers what LLMs are, their use cases, and how prompt tuning can enhance their performance.
They have provided assembled readings on large language models
Additionally, the course introduces Google tools that can assist you in developing your own generative AI applications.
Prerequisites
The course is specifically designed for beginners and does not require any prior experience.
Course Inclusion
- Introduction to large language models
- Reading Inclusion (Reading Resources)
This course is a perfect starting point for those looking to understand the basics of large language models and their practical applications.
This microlearning course is designed to be beginner-friendly, allowing individuals with no prior experience to get a glimpse of the world of generative AI. language models with Google Cloud!
LLM University by Cohere
LLM University is a comprehensive learning resource designed for individuals interested in natural language processing (NLP), from beginners to advanced learners.
It focuses on NLP topics, including large language models (LLMs), making it an ideal platform for those eager to master NLP skills and learn about LLMs.
Prerequisites
LLMU’s curriculum is designed to provide a solid foundation in Language AI for individuals of all backgrounds. Whether you’re a machine learning beginner, an enthusiast looking to build language AI applications, or someone ready to put their skills into practice, LLM University caters to a diverse audience.
Course Inclusion
- Introduction to LLMs
- Text Representation
- Text Generation
- Prompt engineering
LLM University is an excellent resource for anyone interested in mastering NLP and LLM skills and exploring the world of large language models and generative AI.
In addition to the course material, they will be conducting reading groups and hosting events exclusively for all learners!
LangChain Crash Course
This crash course is designed for beginners to learn how to use LangChain, a framework created to simplify the development of applications using large language models.
LangChain enables the seamless integration of AI models with various data sources, making it easy to build customized natural language processing (NLP) applications.
Prerequisites
The course is designed for beginners, so no specific prerequisites are mentioned. However, a basic understanding of programming concepts and a familiarity with AI and NLP fundamentals can be beneficial.
Course Inclusion
- Introduction to LangChain
- First Project – Pets Name Generator
- Exploring Agents within LangChain
- Second Project – YouTube Assistant
- Creating our own Vector Stores
- Discussing LangChain’s Potential Applications
- OpenAI API Costs and Budgeting
If you’re a beginner looking to explore the world of large language models and NLP applications, this crash course on LangChain is a fantastic resource.
With a focus on hands-on projects and simplified use of large language models, you can quickly get started on your journey to building custom NLP applications.
Stable Diffusion Crash Course
This full course is designed for beginners to learn how to use Stable Diffusion, a tool for creating art and images. The course covers various aspects, including training your own model, using Control Net, utilizing Stable Diffusion’s API endpoint, and more.
It also highlights the ethical implications of AI in art and emphasizes responsible usage and respecting the rights of artists.
Prerequisites
The course doesn’t specify any prerequisites, but having a basic understanding of art and AI concepts can be beneficial for a better grasp of the material.
Course Inclusion
- Introduction to Stable Diffusion
- Building and Training Your Own Model
- Introduction to Control Net in Stable Diffusion
- Exploring Stable Diffusion’s API Endpoint
- Navigating Ethical Challenges in AI-Generated Art
- Responsible AI in Art Creation
- Resources for Ongoing Learning
If you’re a beginner interested in creating art and images using Stable Diffusion, this crash course is a valuable resource. It covers all the essentials, from training your own model to using Stable Diffusion’s API endpoint.
The course also highlights the importance of using AI in art responsibly and respecting artists’ rights.
LangChain for LLM Application Development
This course, provided in collaboration with LangChain, is designed for beginners and focuses on using LangChain for Language Model (LLM) Application Development. LangChain is a framework for expanding the use cases and capabilities of language models in application development.
In this course, you will learn how to apply LLMs to your proprietary data, build personal assistants and specialized chatbots, and explore various features of the LangChain framework.
Prerequisites
While the course is beginner-friendly, having basic knowledge of Python can be advantageous to get the most out of it.
Course Inclusion
- Introduction to LangChain and LLMs
- Model Prompts and Parsers
- Memory and Context in LLMs
- Building Chains of Interaction
- Managing Chain Progression and Logic
- Error Handling and Recovery in Chains
- Developing Q&A Systems with LLMs
- Evaluation and Performance Metrics
- Working with Agents in LangChain
- Integrating Agents for Task Automation
- Case Studies of Successful Agent Implementations
If you’re a beginner and want to expand your knowledge in language model application development using LangChain, this course is a valuable resource.
With a focus on practical learning and taught by Harrison Chase and Andrew Ng, this course provides essential skills for leveraging the capabilities of language models in application development.
How Business Thinkers Can Start Building AI Plugins With Semantic Kernel
This course, in collaboration with Microsoft, is aimed at beginners and business thinkers who want to start building AI plugins with Semantic Kernel.
You’ll learn how to utilize Microsoft’s open-source orchestrator, Semantic Kernel, to develop your business planning and analysis skills while leveraging AI tools.
The course covers various aspects of working with Large Language Models (LLMs) and utilizing common building blocks like memories, connectors, chains, and planners.
Prerequisites
Basic Python knowledge and an understanding of an Application Programming Interface (API) are recommended. Familiarity with what a Software Design Kit (SDK) is can be helpful but is not required.
Course Inclusion
- Introduction to Large Language Models (LLMs)
- Introduction to Semantic Kernel
- Overview of Microsoft’s Open-Source Orchestrator
- Developing Effective Prompts
- Exploring Vector Databases
- Managing and Querying Vector Data
- Understanding Semantic Functions and Their Role
- LLMs for Planning and Decision-Making
If you’re a business thinker or beginner interested in building AI plugins and leveraging AI tools for business planning and analysis, this course is a valuable resource.
You’ll learn how to work with Large Language Models (LLMs) and Microsoft’s Semantic Kernel, gaining the skills to create sophisticated business applications using LLMs.
The course also emphasizes using common LLM building blocks and the open-source orchestrator Semantic Kernel. Taught by John Maeda, VP of Design and Artificial Intelligence at Microsoft, this course provides essential knowledge for business applications.
Finetuning Large Language Models
This course, in collaboration with Lamini, focuses on the fundamentals of finetuning large language models (LLMs). Finetuning is a process where you take your own data to train the model, updating the weights of the neural nets in the LLM.
This course will help you understand when to apply finetuning, how to prepare your data for it, and how to train and evaluate an LLM on your data. You’ll also learn how finetuning differs from other methods like prompt engineering and Retrieval Augmented Generation.
Prerequisites
To get the most out of this course, learners are recommended to have Python familiarity and an understanding of a deep learning framework such as PyTorch.
Course Inclusion
- Introduction to Course
- Why Finetune
- Where fine-tuning fits in
- Instruction Finetuning
- Data Preparation and Preprocessing
- Model Training process
- Evaluation and Iteration
If you want to dive into the world of finetuning large language models (LLMs) and understand the techniques and applications involved, this course is a valuable resource.
Taught by Sharon Zhou, a seasoned instructor in the field, the course covers the essentials of when and how to apply finetuning, data preparation, and the training and evaluation of LLMs using your own data.
Building Systems with the ChatGPT API
This short course, in collaboration with OpenAI, focuses on “Building Systems with the ChatGPT API.” It is designed to teach learners how to efficiently build multi-step systems using large language models.
By splitting complex tasks into a pipeline of subtasks using multistage prompts, you will learn how to automate complex workflows and improve your efficiency.
Prerequisites
You only need a basic understanding of Python to complete this course. It is also suitable for intermediate or advanced machine learning engineers who want to enhance their prompt engineering skills for LLMs.
Course Inclusion
- Language Models, the Chat Format, and Tokens
- Classifications
- Moderation
- Chain of Thoughts reasoning
- Chaining Prompts
- Evaluation- I and II
If you’re looking to enhance your skills in building systems with the ChatGPT API, this course is a valuable resource. From the basics to advanced concepts, you’ll learn how to create chains of prompts, work with Python code, and build a customer service chatbot.
The practical skills you gain can be applied to various real-world scenarios, making it a worthwhile investment of your time. Taught by industry experts and available for free for a limited time, this course is your opportunity to explore and master the capabilities of large language models.
Enroll now and start building complex systems efficiently!
Vector Embeddings Tutorial
This tutorial is all about understanding and using vector embeddings in your machine learning and artificial intelligence projects.
It teaches you how to create an AI assistant with vector embeddings using OpenAI’s GPT-4 API, LangChain, and Natural Language Processing (NLP) techniques.
Prerequisites
The course doesn’t specify prerequisites, but a basic understanding of machine learning concepts and some familiarity with programming would be helpful.
Course Inclusion
- Understanding Vector Embeddings
- Creating Text Embeddings with OpenAI
- Working with Vector Databases
- Introduction to Langchain
- Building an AI Assistant
- Hands-On: Building an AI Assistant
If you’re looking to enhance your knowledge of vector embeddings and learn how to create an AI assistant using GPT-4, LangChain, and NLP techniques, this tutorial is a great resource.
Vector embeddings are a fundamental concept in modern AI, and understanding how to work with them is valuable.
Large Language Models with Semantic Search
This course is all about enhancing keyword search by incorporating large language models and semantic search techniques.
You’ll learn how to use Cohere Rerank and embeddings to improve keyword search results, making the user experience more effective and efficient.
Prerequisites
The course is labeled as “Beginner,” but having a basic familiarity with Python is recommended to get the most out of the content. Some understanding of search and keyword-based retrieval systems can also be beneficial.
Course Inclusion
- Enhancing keyword search with semantic search
- Embedding
- Dense Retrieval
- ReRank
This course helps you grasp the essential techniques and concepts for making your search systems smarter and more efficient.
If you’re looking to enhance your search capabilities, this course is a great resource. Enroll now and take your keyword search to the next level with semantic search techniques!
Evaluating and Debugging Generative AI Models
This course focuses on the vital skill of evaluating and debugging generative AI models, whether it’s large language models (LLMs) or generative image models. It offers insights into using platform-independent tools to track, monitor, and evaluate these models effectively.
Prerequisites
The course is aimed at intermediate-level learners. You should have some familiarity with Python and experience with frameworks like PyTorch or similar. A background in machine learning or AI projects is beneficial but not strictly required.
Course Inclusion
- Instrument W & B
- Training Diffusion Model with W & B
- Evaluating Diffusion Models
- LLM Evaluation and Tracing with W & B
- Finetuning a Language Model
The ability to evaluate and debug generative AI models is crucial in the world of AI and machine learning. This course equips you with valuable skills and tools to effectively manage, monitor, and evaluate your projects.
Using the Weights & Biases platform, you’ll streamline your workflow, enabling you to track experiments, manage data, and collaborate efficiently.
Instructor Carey Phelps, a Founding Product Manager at Weights & Biases, brings her expertise to help you master this critical aspect of AI development. If you’re looking to enhance your machine learning operations skills and effectively evaluate and debug generative AI models, this course is an excellent choice. Enroll now to take your AI projects to the next level!
LangChain: Chat with Your Data
This short course provides an opportunity to learn directly from Harrison Chase, the creator of LangChain, a powerful framework designed to simplify the creation of applications using large language models (LLMs).
In this course, you’ll dive into two main topics: Retrieval Augmented Generation (RAG), a common LLM application, and building a chatbot that responds to queries based on the content of your documents.
Prerequisites
This course is beginner-friendly but assumes that you are familiar with Python. It’s ideal for developers interested in creating applications using large language models like ChatGPT. If you have some Python skills and want to leverage LLMs for your projects, this course offers practical knowledge and hands-on experience.
Course Inclusion
- Document Loading
- Document Splitting
- VectorStores and Embedding
- Retrieval
- Chat With LLM
LangChain is a valuable framework for simplifying the creation of applications using large language models. If you’re eager to learn how to harness the power of LLMs to build applications that can interact with data, this course is an excellent choice.
By learning directly from Harrison Chase, you’ll be equipped with the knowledge and skills needed to work with LangChain effectively.
Whether you’re interested in Retrieval Augmented Generation (RAG) or building chatbots that respond to document content, this course provides a practical path to creating applications that chat directly with your data.
Building Generative AI Applications with Gradio
This short course offers you the opportunity to learn from Apolinário Passos, a Machine Learning Art Engineer at Hugging Face. The focus of the course is on creating generative AI applications using Gradio, a user-friendly platform for building machine learning applications.
You’ll be able to quickly build and demo machine learning applications, share them with others, and gain practical knowledge for your projects.
Prerequisites
This course is beginner-friendly, but some basic Python knowledge is recommended. If you have a basic understanding of Python and want to quickly build and share applications and demos using Gradio, this course provides a great opportunity to do so.
Course inclusion
- NLP Tasks Interface
- Image Captioning App
- Image Generation APP
- Describe and generate
- Chat With any LLM
In the world of AI and machine learning, building practical applications is a crucial skill. This short course on Building Generative AI Applications with Gradio allows you to do just that.
Whether you want to create text summarization apps, image captioning tools, text-to-image generation interfaces, or even chatbots with open-source large language models, this course equips you with the knowledge to do so efficiently.
Development with Large Language Models Tutorial
This course, created by Akshath, focuses on developing Large Language Models (LLMs) to harness their capabilities for various projects. Throughout the course, you’ll engage in hands-on projects that will enable you to work effectively with LLMs.
The projects you’ll undertake cover building dynamic interfaces, interacting with vast amounts of text data, and empowering LLMs to browse the internet for research papers.
Prerequisites
The prerequisites for this course may vary depending on the specific projects and content covered. However, having a basic understanding of Python is generally recommended for working with LLMs. Each project may have its own prerequisites, so it’s advisable to review the content and projects included in the course for more specific requirements.
Course Inclusion
- Introduction to LLMs
- ChatGPT Playground and GPT API
- Building with ChainLit
- Working with Vector Databases
- Implementing Q&A with Documents (TXT and PDF)
- Web Browsing and Agents
- Building a Mini Code Interpreter Plugin (Replit Tool)
- Extending Functionality with Agents
- Shell Tool and Custom Tool Creation
Development with Large Language Models Tutorial is a comprehensive course that takes you through a series of hands-on projects, empowering you to harness the capabilities of LLMs for your projects.
Whether you’re interested in creating dynamic interfaces, working with text data, or conducting internet research with LLMs, this course equips you with the skills and knowledge to get started.
Enroll now and start building projects that leverage LLMs for various applications.
Build AI Apps with ChatGPT, DALL-E, and GPT-4
This full course, created by Tom Chant, a teacher at Scrimba, is designed to teach you how to build AI-powered apps using the ChatGPT, DALL-E, and GPT-4 APIs.
The course covers various aspects of developing AI applications, and it includes hands-on projects to help you learn and apply your knowledge.
Prerequisites
The course recommends having a basic understanding of HTML, CSS, and JavaScript before taking it. It’s also recommended that you learn some essential web development skills, as the course focuses on building AI applications for the web.
Course Inclusion
- MoviePitch – Creating a Pitch Generator
- Setting Up the Boilerplate
- Exploring Models and Tools
- Implementing fetchSynopsis
- Understanding Tokens
- Adding Image Generation with createImage and Completing UX
- KnowItAll – GPT-4 Chatbox
- Understanding How ChatGPT Models Work for Chatbots
- Leveraging the Create Chat Completion Endpoint
- Firebase Setup and Database Configuration
- Managing Conversations in the Database
- Converting the Chatbot to We-Wingit
- Setting Up the Environment for Fine-Tuning
- Tuning the model and Updating JavaScript for Deployment
- Deployment and Hosting on Netlify
- Download, GitHub, and Environment Variables
- Implementing Netlify Serverless Functions
This is a comprehensive course for beginners interested in creating AI-powered applications. Whether you’re looking to build interactive interfaces, chatbots, image generation apps, or fine-tuned chatbots, this course covers a range of topics and provides hands-on projects to apply your knowledge.
If you’re looking to get started with AI app development, this course is an excellent resource. Enroll and start building your AI-powered applications today.
Final Words
In this article, we have explored various free courses that will help you learn all the necessary concepts in-depth, along with hands-on projects. Make sure to complete all the necessary exercises while learning; it will improve your understanding.
When you’re ready to start building, check out our popular AI models to build generative AI applications.
