implementation detail · filed under model architecture
Kernel-4 convolutional layers in decoder blocks
Decoder-block implementation that applies kernel-4 convolutions after key and value projections and to attention and MLP branch outputs.
- 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 decoder layer applies short kernel-4 convolutions after the key and value projections and on the attention and MLP branch outputs.
usedmodel architecturein InklingThinking Machines Lab
Filed alongside
Other methods under model architecture :: token mixer.