Open Models Almanac
Methodsmodel architecturetoken mixersoftmax attention

filed under model architecture

Cascade attention

A named attention mechanism indicated only by its configuration flag; its operation is not established by the evidence.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See softmax attention for the methods filed beside it.

sources
2
model
1
labs adopt it
0
strongest
not used
↑