Open Models Almanac
Methodspost-trainingsupervised fine-tuning

single mention · post-training

Cold-started supervised fine-tuning model

An SFT model used as the starting point for subsequent reinforcement learning.

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 cold-started SFT model.

Filed under post-training › supervised fine-tuning