Model techniques map
Techniquesmodel architecturetoken mixersoftmax attention

ambiguous · filed under model architecture

Attention layers

The evidence identifies attention layers but does not specify a more distinct attention mechanism.

source
1
model
1
lab adopt it
1
strongest
core

How sources treat it

One count per evidence span, weakest treatment to strongest.

core 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

select Attention layers

coremodel architecturein Nemotron 3 UltraNVIDIA

Filed alongside

Other methods under model architecture :: token mixer :: softmax attention.