They literally banned the following mathematics:
Attention(Q, K, V) = softmax(QK^T / sqrt(d_k))V
🤣
Italians look away please, you are not supposed to see this formula.
They literally banned the following mathematics:
Attention(Q, K, V) = softmax(QK^T / sqrt(d_k))V
🤣
Italians look away please, you are not supposed to see this formula.