The following are the answers to the questions given at the end of each chapter.
Chapter 1, A Primer on Transformers
- The steps involved in the self-attention mechanism are given here:
- First, we compute the dot product between the query matrix and the key matrix
and get the similarity scores. - Next, we divide
by the square root of the dimension of the key vector 
. - Then, we apply the softmax function to normalize the scores and ...
