Part of the TechAarvam workshop support files — Build Your Own Model . Attention is simpler than you think A hand-crafted superhero transformer This notebook presents a hand-crafted example. The goal is to understand the intuition behind the attention block in the transformer architecture. Attention and FFN are the two main components. FFN is an Artificial neural network (ANN) with 1 input, 1 hidden, and 1 output layer. So we start constructing the FFN's job ...