The world of Large Language Models (LLMs) is filled with noise and every day there are random courses, cheat sheets, and tools that can make beginners even more confused about the whole field. Do they start with fine-tuning language models, learn about Langchain, or just stick to Natural Language Processing (NLP) basics? There is so much content out there that it has become difficult to navigate.
So, for beginners, I have curated a list of free resources that will help them learn about LLMs and improve their building of AI applications. These resources include free courses, tutorials, blogs, boot camps, roadmaps, and an awesome list of tools and services.
1. KDnuggets (Language Models)
The Language Models category on KDnuggets.com contains the most helpful and easy-to-follow guide on building AI applications or learning new concepts. I know I write on KDnuggets and am biased but for the right reasons. We make sure the topics that we cover are important and help you build an AI project with limited resources and require minimal effort. The Language Models category on KDnuggets consists of blogs, tutorials, guides, and opinion blogs that will help you fine-tune the LLMs, use them locally, build the RAG application, and more. We are always looking for popular topics to cover, and it is the best place for you to get your daily latest knowledge on LLMs.
2. DataCamp Tutorials
If you are looking for detailed tutorials on LLMs that provide a step-by-step guide to building an AI application, then you should bookmark DataCamp’s AI tutorials page. It covers topics like fine-tuning, using LLMs locally, building a project with OpenAI API, serving LLMs, vector databases, the latest LLM orchestration frameworks, and so much more. Each tutorial in this category is a proper project that you can build and add to your resume.
3. LLM Zoomcamp
The LLMs Zoomcamp is an online bootcamp designed to teach practical applications of LLMs and Retrieval-Augmented Generation (RAG). It covers essential topics such as setting up environments, retrieval basics, and using the OpenAI API, along with implementing simple RAG systems and text searches with Elasticsearch. The course also explores open-source LLMs on Hugging Face. Participants will learn about vector databases and vector search, offline evaluation methods, and tracking and visualizing performance with tools like Grafana.
4. Generative AI for Beginners by Microsoft
The Generative AI for Beginners by Microsoft, available on GitHub, offers 18 comprehensive lessons designed to introduce beginners to the world of generative AI, including LLMs. This free online resource provides a thorough understanding of key concepts and techniques, making it accessible to anyone eager to explore LLMs. Participants will learn the fundamentals of generative AI and LLMs, comparing and exploring different LLMs, responsible usage of generative AI, prompt engineering basics, building text generation and search applications, working with vector databases, and securing generative AI applications, among others.
5. CS324 – Large Language Models by Stanford University
Stanford University’s CS324 is an academic course that introduces you to the fundamentals of modeling, theory, ethics, and systems aspects of LLMs, offering students hands-on experience in working with these advanced technologies. The course comprehensively covers both the theoretical foundations and practical applications of LLMs, making it an invaluable resource for anyone seeking to understand the intricate workings of these powerful models.
6. LLM University by Cohere
The LLM University (LLMU) by Cohere is a free course taught by experts in the field. It comes with a step-by-step guide for you to start building an AI application for free without a technical background. The course covers the basics of LLMs, test representation, text generation, deployments, semantic search, Prompt engineering, Retrieval-Augmented Generation (RAG), and Tool use. It covers everything from the basics to advanced concepts in LLMs.
7. Large Language Models Roadmap
The Large Language Models Roadmap is a GitHub repository that takes the structured approach of learning LLMs one module at a time. It includes roadmaps, example Colab notebooks, and various resources to offer hands-on experience with LLMs. The course is divided into three parts: LLM Fundamentals, The LLM Scientist, and The LLM Engineer. So, in short, it is for everyone: beginners, experts, enthusiasts, and even senior engineers.
8. Full Stack LLM Bootcamp
The Full Stack LLM Bootcamp course was started as a deep learning free bootcamp but evolved into the LLMs bootcamp. It will teach you the best practices and tools used by experts in the field. You will start with prompt engineering and eventually move on to advanced topics, integrating multiple solutions and deploying the AI application. The Bootcamp is for individuals who have a technical background in the field and want to know more about the world of LLMs.
9. NLP Course by Hugging Face
The Hugging Face NLP course is not your typical LLM course, but it is for you to build fundamentals in natural language processing. You will learn about Transformers models, fine-tuning and saving them, understanding the dataset and tokenizer library, and performing main NLP tasks. NLP is a prerequisite for jumping into the field of LLMs. It would help if you learned to handle text data and understand how to train the model on them. At the end of the course, you will learn to deploy the model and application and share it with your friends and colleagues.
10. Awesome-LLM
The Awesome LLM is a curated list of tutorials, papers, tools, and other resources to help you learn about and work with LLMs. The open-source community regularly updates this repository and provides the latest information for anyone interested in LLMs. It is organized into various topics, including Milestone Papers, LLM Leaderboard, Open LLM, LLM Data, LLM Evaluation, LLM Training Framework, LLM Deployment, LLM Applications, and LLM Books, among others. All you have to do is bookmark it and return to it weekly so you don’t miss anything related to LLMs.
ConclusIon
Cutting through the noise and bookmarking the best content on LLMs is the most efficient way to learn about these models quickly and for free. I highly recommend a hands-on learning approach: choose a project, start researching it on Google, and eventually build an AI application. Even if you lack prior knowledge of working with text data, you will gradually learn by reading blogs, tutorials, taking courses, and attending bootcamps. The key is to build projects and document your progress. Showcasing your learning journey will attract others who are interested in working with you on similar topics.
Image by Author | ChatGPT & Canva
