Open Models Almanac
Methodsmodel architecturechannel mixermixture of experts

single mention · model architecture

MoE layer densification by expert concatenation

A training-time modification that converts selected MoE layers into dense FFNs by concatenating a shared expert with selected routed experts.

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

Filed under model architecture › channel mixer › mixture of experts