If you're working with LLMs or any transformer based model, you probably have hit a real problem like slow inference, an out of memory error, or
frustrating hallucinations. So, you know that understanding the pieces [music] isn't the same as understanding how they all fit together and then how
you can action on them and debug these issues by understanding how the transformer [music] and the LLM
system around it really work. I'm Sharon Joe and this is Transformers in Practice [music] built in collaboration with Deep Learning AI and AMD. You
might find that those explanations don't connect to the problems you're actually facing. To address that, this course gives you the complete practical
view so you can gain deeper intuition in a way that impacts how you can practically use LLMs. This
includes how transformers generate text one token at a time, what attention really is doing, and how it all gets optimized to run [music] on GPUs.
Throughout the course, interactive visualizations will let you see and play with key technical pieces and how they come together coherently.
Transformers in Practice is available now and I'll see you there.