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.
Mixture of ExpertsSparse expert activationDeepSeekMoEGated DeltaNet MoEMixture-of-Experts layersMoE with routed and shared expertsAsymmetric input/output activation splitDispatch recomputationFrequency-based partitioning of N-gram embedding slotsHybrid Mixture of ExpertsMegaMoEMoE with 128 routed experts and a shared expertMoE with 384 routed experts and a shared expertOutput-independent MoE gradient reformulationRouted expert output modulationSigmoid-based MoE router with auxiliary-loss-free load balancing