Open Models Almanac
Methodspost-trainingpolicy distillation

specific method · filed under post-training

Distillation from a Larger Nemotron 3 Model

Large-scale distillation using the next-larger Nemotron 3 model as teacher; evidence does not identify a more specific algorithm.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See policy distillation for the methods filed beside it.

Also called distilled each model for 1 trillion tokens.

sources
2
models
2
lab adopt it
1
strongest
used

Documented in

Evidence

2 quotes from 2 sources, one card per model, each opening with its strongest.

How sources treat it
used 2

followed by 1 trillion tokens of distillation from the next-larger Nemotron 3 model

usedtraining objectivein NVIDIA Nemotron 3.5 Super and NVIDIA Nemotron 3.5 LightningNVIDIA
1 more from this model

then distilled each model for 1 trillion tokens

usedtraining objectivein Nemotron 3.5 Super and Nemotron 3.5 LightningNVIDIA
↑