Model techniques map
Techniquesmodel architecturetoken mixersoftmax attentionsliding window attention

ambiguous · filed under model architecture

Per-Head Gating

A per-head gating configuration associated with sliding-window attention; the evidence gives θswa = 10,000 but does not specify further mechanics.

Also called Per-head gating with θswa=10,000, + per-head gating, θswa = 10,000.

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.

+ per-head gating, θswa = 10,000

evaluatedmodel architecturein Laguna XS.2Poolside

Filed alongside

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