Model techniques map
Techniquesmodel architecturetoken mixersoftmax attentionsliding window attention

specific method · filed under model architecture

SWA-1024

Sliding Window Attention using a 1024-token window, interleaved at a 3:1 ratio.

Also called + SWA-1024 (interleaved 3:1).

source
1
model
1
labs adopt it
0
strongest
evaluated

How sources treat it

One count per evidence span, weakest treatment to strongest.

evaluated 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

+ SWA-1024 (interleaved 3:1)

evaluatedmodel architecturein Laguna XS.2Poolside

Filed alongside

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