From the course: NVIDIA Certified Associate AI Infrastructure and Operations (NCA-AIIO) Cert Prep

Unlock this course with a free trial

Join today to access over 25,300 courses taught by industry experts.

Transformer model

Transformer model - NVIDIA Tutorial

From the course: NVIDIA Certified Associate AI Infrastructure and Operations (NCA-AIIO) Cert Prep

Start my 1-month free trial Buy for my team

Transformer model

“

I'm pretty sure you have heard about transformer model. It has revolutionized the way we interact with these machine learning models. Let's talk a little bit on the transformer model. So transformer model architecture is basically coming from a white paper which is called attention is all you need. An attention enabled model to scale the understanding of relationship between words. So it allowed our machines to understand relationship between words and that allowed us to create new content and that efficiently uses parallel computing which requires because it requires lots and lots of calculation at the given time. So what is transformer model let me give you a very basic example you don't need to learn about this whole aspect but if you are interested go ahead and read a white paper called attention is all you need which is like a fundamental aspect of how generative AI works. Let me give a very basic example to explain how this transformer model actually works. So let's consider…

Contents