Learn the fundamentals of large language models (LLMs) and put them into practice by deploying your own solutions based on open source models. By the end of this course, you will be able to leverage state-of-the-art open source LLMs to create AI applications using a code-first approach. You will start by gaining an in-depth understanding of how LLMs work, including model architectures like transformers and advancements like sparse expert models. Hands-on labs will walk you through launching cloud GPU instances and running pre-trained models like Code Llama, Mistral, and stable diffusion. The highlight of the course is a guided project where you will fine-tune a model like LLaMA or Mistral on a dataset of your choice. You will use SkyPilot to easily scale model training on low-cost spot instances across cloud providers. Finally, you will containerize your model for efficient deployment using model servers like LoRAX and vLLM. By the end of the course, you will have first-hand experience leveraging open source LLMs to build AI solutions. The skills you gain will enable you to further advance your career in AI.
ND
Great learning resources that will be useful long after completing the course, concise presentations, and clear explanations of all topics
显示：4/4
Great learning resources that will be useful long after completing the course, concise presentations, and clear explanations of all topics
Very educational, especially the RAG part.
Exceptional series of courses
Generally a very interesting specialization. Especially the parts presented by Alfredo were well structured and providing the needed insights into the concepts, challenges and tools. The labs were also very helpful for hands-on experience. Great! However it was evident and annoying, that a significant part of the material was added just to boost the volume or rather as a precondition to have the Duke's logo on it, absolutely missing the point of the course. Like focusing on solving some beginner level pure low level programming tasks inside the course on Databricks and LLMs. Why? Quite detached from real world business tasks, which is not unusual for universities, though. And, I agree, Rust is cool for certain tasks, but it was a bit too much of pushing it repeatedly. However all in all, very informative, my recommendations, helpful and interesting, thanks a lot!