Model techniques map
Techniquesmodel architecturechannel mixermixture of expertsshared experts

specific method · filed under model architecture

Shared Experts Active on Every Token

A configuration in which shared experts are active for every token, in addition to routed experts.

Also called 2 shared experts active on every token.

sources
2
model
1
lab adopt it
1
strongest
core

How sources treat it

One count per evidence span, weakest treatment to strongest.

core 2

Documented in

Evidence

2 spans quoted from the sources, strongest treatment first.

each token is routed to 6 of 256 experts, plus 2 shared experts active on every token

coremodel architecturein InklingThinking Machines Lab

plus 2 shared experts active on every token

coremodel architecturein InklingThinking Machines Lab

Filed alongside

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