Model techniques map
Techniquesmodel architecturechannel mixermixture of experts

implementation detail · filed under model architecture

MoE with 256 experts and top-8 routing

An MoE configuration with 256 experts and eight routed experts activated per token; the evidence does not establish whether it has a shared expert.

Also called Sparse MoE with 256 experts and 8 top-k.

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.

Each MoE layer comprises 256 experts in total, with 8 activated per token, and contains no shared experts.

usedmodel architecturein MiMo-V2-FlashXiaomi

Filed alongside

Other methods under model architecture :: channel mixer :: mixture of experts.