Open Models Almanac
Methodspost-trainingsupervised fine-tuning

single mention · post-training

Training a downstream policy only on high-quality task data

Trains the downstream policy exclusively on a selected high-quality task dataset.

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

Also called training on only this high-quality data.

Filed under post-training › supervised fine-tuning