Model techniques map
Techniquespost-trainingsupervised fine-tuning

specific method · filed under post-training

Light SFT on teacher-distribution data

A light supervised fine-tuning stage using data drawn from a teacher's training distribution.

Also called teacher-distribution SFT warmup.

source
1
model
1
lab adopt it
1
strongest
core

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1core 1

Documented in

Evidence

2 spans quoted from the sources, strongest treatment first.

the student undergoes a very light SFT on data drawn from the teacher’s training distribution.

coreunclearin Nemotron 3 UltraNVIDIA

before pivot RL, we performed light SFT directly on the student Ultra model.

usedunclearin Nemotron 3 UltraNVIDIA

Filed alongside

Other methods under post-training :: supervised fine-tuning.