implementation detail · filed under model architecture
Alternating Row-Major and Column-Major Token Serialization
An implementation detail that alternates token serialization order across local SWA layers to propagate information along both spatial axes.
- source
- 1
- models
- 2
- 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.
Local SWA layers alternate between row-major and column-major token serialization to support information propagation along both spatial axes.
coremodel architecturein MiMo-ViTXiaomi
Filed alongside
Other methods under model architecture :: token mixer :: softmax attention :: sliding window attention.