Hi Mentor, In this transformer architecture assignment, in the encoder layer why its not happening weight matrix multiplication like Q=WX, K=WX. can you please help to understand why not happening ?

Transformer Architecture Assignment

TMosh May 11, 2022, 2:56pm 5

This one:

Topic		Replies	Views
Encoder Layer Mask Purpose Sequence Models coursera-platform	6	645	May 11, 2022
Week 4: Transformer Network (test time intuition) Sequence Models coursera-platform	1	516	April 21, 2022
W4 - Assignment: Why do we only update the attention weights in the decoder, but not in the encoder? Sequence Models coursera-platform	2	535	December 2, 2022
A question of Transformer Sequence Models coursera-platform	1	492	December 3, 2021
Conceptual Questions about Transformers Sequence Models coursera-platform	13	672	April 23, 2023