specific method · filed under model architecture
SiTU
A custom activation function identified as replacing standard GeLU or SwiGLU.
Also called Sigmoid Tanh Unit (SiTU).
- 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.
Sigmoid Tanh Unit (SiTU): Custom activation function replacing standard GeLU/SwiGLU
usedmodel architecturein Kimi K3Moonshot AI
Filed alongside
Other methods under model architecture :: channel mixer :: dense feed-forward network.