Introduction
The rise of large language models (LLM) like ChatGPT has been revolutionary and ushered in a new era in the way we interact with technology. These sophisticated models, exemplified by ChatGPT, have redefined how we interact with digital platforms. Think about it: how often have you used tools like ChatGPT to effortlessly write an email or employed generative ai to bring your wildest imaginations to life through stunning images? This relentless evolution of generative ai technology is not just a scientific advancement; It is a gateway to infinite creative possibilities, reshaping our digital landscape at an impressive pace. However, there is a notable gap in this whirlwind of rapid progress. While we marvel at the results of generative ai, a deeper understanding of its foundations and practical applications remains elusive for many. This is where this blog comes in. Introducing a solution: generative ai resources.
I've meticulously compiled a ranked list of the best generative ai courses to give you this cutting-edge knowledge. This is not just a list; is your roadmap to unraveling the magic behind these incredible tools. Whether you are a curious student, an aspiring ai enthusiast, or a professional looking to improve your skills, these courses satisfy your thirst for knowledge.
<h2 class="wp-block-heading" id="h-list-of-generative-ai-resources-for-you”>List of Generative ai Resources for You
<h3 class="wp-block-heading" id="h-step-1-how-do-you-get-started-with-generative-ai“>Step 1: How to get started with Generative ai?
If you are a beginner in generative ai, start with this course at ai-for-everyone” target=”_blank” rel=”noreferrer noopener nofollow”>Generative ai for everyone. In this Generative ai course, you will explore how generative ai works, common use cases, and capabilities. You will also learn how to create effective prompts and understand the potential opportunities and risks that this technology poses to people, businesses, and society.
Now, the next thing you need to learn is how to use popular generative ai tools like ChatGPT, Midjourney, and more. In this course on Generative ai tools, you will learn exactly that. You'll understand the basics of generative ai, learn about the most popular tools for text and image generation, and even how to use them for various applications such as image editing, email crafting, visual content creation, and more.
<h4 class="wp-block-heading" id="h-additional-generative-ai-resources”>Additional Generative ai Resources
- “The State of GPT” by Karpathy: Look here
- A gentle introduction to generative ai for beginners: ai-for-beginners-8c8752085900″ target=”_blank” rel=”noreferrer noopener nofollow”>Read here
Step 2: Where to learn about rapid engineering?
Once you've learned about generative ai, the next step is to play with the technology and fall in love with its possibilities. The best way to do this is to play with ChatGPT. But did you know that even to get the most out of ChatGPT, you need to learn about Prompt Engineering? Now you ask, what is that? Well, it is the way we interact with an LLM and get the desired outcome.
To learn that, you can start with this. course by Codecademy on rapid engineering. This will help you get started with the basics. If you want to move on to something detailed, I highly recommend this guide on ai/” target=”_blank” rel=”noreferrer noopener nofollow”>Quick engineering, which is nothing less than a course. Although this is an extensive guide, it is well structured and covers prompt engineering comprehensively, including topics such as zero-shot learning, few-shot learning, and chain-of-thought learning. It also gives you general tips for designing good messages that effectively solve any use case.
<h4 class="wp-block-heading" id="h-additional-generative-ai-resources-0″>Additional Generative ai Resources
Step 3: How do you learn about LLMs?
Now that you've interacted with ChatGPT using the standard OpenAI interface, it's time to move on to designing your own systems using the ChatGPT API. For that, you can explore in this course on ai/short-courses/building-systems-with-chatgpt/” target=”_blank” rel=”noreferrer noopener nofollow”>Building systems with the ChatGPT API by DeepLearning.ai. Here, you will learn to break down complex tasks into smaller tasks and solve them using prompts. This will show you how to use a powerful tool like ChatGPT for your specific tasks.
Once this is done, you will be able to create your first LLM-based application using the LangChain framework in this course on ai/short-courses/langchain-for-llm-application-development/” target=”_blank” rel=”noreferrer noopener nofollow”>LangChain for LLM Application Development. LangChain is an open source framework for developing LLM-powered applications that are not limited to ChatGPT. It enables the creation of context-aware applications by connecting LLM with data and providing tools for personalization, accuracy, and relevance. In this course, you will learn how to create an LLM application using LangChain, which will get you accustomed to creating personal assistants and chatbots.
What if standard LLMs have static knowledge and you want to augment it to suit your particular use case? That is when you will need to use the RAG technique to augment LLMs and build your application. So what is RAG? Well, RAG stands for Recovery Augmented Generation. It is a strategy in which you provide additional knowledge to the LLM through a retrieval system. This allows the LLM to answer more specific queries even if they are not trained in it. You can learn about RAG and more in this ai/short-courses/building-evaluating-advanced-rag/” target=”_blank” rel=”noreferrer noopener nofollow”>Building and testing advanced RAG applications course.
Now that you've built a RAG system, you'll notice that it has some limitations. On the one hand, you will notice that you will not always be able to use all the data retrieved in a message, which limits the response of the LLM. Another would be the hallucinatory effect of LLM, which is difficult to eliminate. So wouldn't it be better to completely adjust your model and get a more personalized LLM? That's what you'll cover. ai/short-courses/finetuning-large-language-models/” target=”_blank” rel=”noreferrer noopener nofollow”>in this gradewhere you will learn about fitting, when to apply it, how to prepare data for fitting, and how to train and evaluate your fitted model.
<h4 class="wp-block-heading" id="h-additional-generative-ai-resources-1″>Additional Generative ai Resources
“Introduction to Large Language Models” by Karpathy: Look here
- The video provides a one-hour introductory overview of LLMs suitable for a general audience, serving as a fundamental technical element in systems such as ChatGPT, Claude, and Bard. You will understand the nature, future directions, and comparisons between these models.
“A Hacker's Guide to Language Models” by Jeremy Howard: Look here
- In this insightful video, Jeremy Howard, co-founder of fast.ai, provides a comprehensive exploration of language models. The video includes critical evaluations of GPT-4, practical applications in writing code and data analysis, and practical tips for using the OpenAI API.
“Catching up with the strange world of LLMs” by Simon Willison: Read here
- The blog covers the essential aspects of language models, exploring their definition, functioning and a concise timeline of developing an LLM. Identifies the best LLM models and offers practical advice, including using them for coding. The blog will also give you a brief overview of how LLMs are trained.
What are Analytics Vidhya Large Language Models (LLM)? Read here
- The blog explores Large Language Models (LLM), delving into their construction and operation. It covers its general architecture, provides examples, discusses open source LLMs such as Bloom, explores Hugging Face APIs, and presents practical applications through examples.
Step 4: What about RLHF?
You must have heard about RLHF. RLHF stands for Reinforcement Learning from Human Feedback. It is a machine learning technique that trains a “reward model” directly from human feedback and uses the model as a reward to optimize the performance of an ai agent through reinforcement. Now, learn about RLHF in this course ai/short-courses/reinforcement-learning-from-human-feedback/” target=”_blank” rel=”noreferrer noopener nofollow”>Deep learning.ai
<h4 class="wp-block-heading" id="h-addition-generative-ai-resources”>Add generative ai resources
Step 5: Where do you learn about diffusion models?
Now, generative ai is not just about LLM. If you want to learn about image generation using generative ai, you need to learn about diffusion models and how they work. For this, there is an impressive Hugging Face course. The course material, including notebooks, reading material and everything else, can be found in this GitHub repository. Here you can find content on basic diffusion models, stable diffusion, tuning a diffusion model, and more.
<h4 class="wp-block-heading" id="h-additional-generative-ai-resources-2″>Additional Generative ai Resources
<h2 class="wp-block-heading" id="h-bonus-comprehensive-generative-ai-program”>Bonus: Comprehensive Generative ai Program
I know there are many courses to take and they are not completely exhaustive. That's why I suggest this comprehensive program on generative ai called Generative ai Pinnacle program. This program covers generative ai from start to finish. Covers topics such as Prompt Engineering, RAG system using LlamaIndex, and LLM tuning including LoRA, QLoRA, PEFT, and Stable Diffusion.
Conclusion
I hope you found this list of generative ai resources useful and that you at least signed up for one of the courses above. However, there are many other courses that I have omitted here. If you find a relevant course on Generative ai, please share it in the comments below. I'd love to explore that myself!