implementation detail · filed under model architecture
Shared-weight design across prediction heads
An MTP implementation that shares weights across prediction heads.
- 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.
The model includes Multi-Token Prediction (MTP) layers using a shared-weight design across prediction heads
usedmodel architecturein Nemotron 3 UltraNVIDIA
Filed alongside
Other methods under model architecture :: prediction head.