Model techniques map
Techniquesmodel architectureprediction head

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.