Model techniques map
Techniquesmodel architecturetoken mixerhybrid layer stacking

implementation detail · filed under model architecture

Gated Attention and Sliding-Window Attention Configuration

A specific attention-head configuration combining gated-attention and sliding-window-attention heads with a dense-attention setting.

source
1
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

+ 48 GA / 64 SWA Q-heads, 𝑘dense=1 (final ablation architecture)

usedmodel architecturein Laguna XS.2Poolside

Filed alongside

Other methods under model architecture :: token mixer :: hybrid layer stacking.