implementation detail · filed under model architecture
Top-8 Routed-Expert Selection with Shared-Expert Activation
Each token activates the top-8 routed experts along with a shared expert.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- core
How sources treat it
One count per evidence span, weakest treatment to strongest.
core 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
every token activates the top-8 routed experts along with the shared expert
coremodel architecturein Hy4-previewTencent Hunyuan
Filed alongside
Other methods under model architecture :: channel mixer :: mixture of experts :: shared experts.