Open Models Almanac
Methodsmodel architecturetoken mixersoftmax attentionsliding window attention

single mention · model architecture

Per-Head Gating

Adds per-head gating to attention; the supplied mention specifies θswa = 10,000.

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

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

Filed under model architecture › token mixer › softmax attention › sliding window attention