Open Models Almanac
Methodspost-trainingsupervised fine-tuning

single mention · post-training

Reasoning-effort assignment in SFT

Assigns reasoning effort levels in SFT configurations.

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 assignment of reasoning effort.

Filed under post-training › supervised fine-tuning