Fixed a formula over Attention

This commit is contained in:
Christian Risi 2025-11-04 15:26:54 +01:00
parent 65288793ce
commit e8197d7abc

View File

@ -88,7 +88,7 @@ $$
\begin{aligned}
Head_i = softmax\left(
\frac{
Q_{i} \times K_{i}
Q_{i} \times K_{i}^T
}{
\sqrt{H}
}