Working Notes: a commonplace notebook for recording & exploring ideas.
Home. Site Map. Subscribe. More at expLog.
This is an attempt at consolidating my understanding of Deep Learning, transformers, and the underlying systems, with implementations to consolidate what I know. I'd like to wrap this up within 2023, and be able to simply explain a transformer model, the calculations that go into it and the infrastructure it takes to build it out.
The notes here are meant for myself and not for consumption by others.
— Kunal