Model techniques map
Techniquesmodel architecturetoken mixersparse attention

ambiguous · filed under model architecture

Natively trained sparsity

The evidence provides only this broad description and does not identify a more specific method.

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.

Most likely natively trained sparsity.

usedtraining objectivein MiniMax-M3MiniMax

Filed alongside

Other methods under model architecture :: token mixer :: sparse attention.