Open Models Almanac
Methodspost-trainingmid-training & continual pretraining

single mention · post-training

Mid-training with lower-quality SFT datasets

A data-staging choice that assigns certain datasets to mid-training rather than supervised fine-tuning.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See mid-training & continual pretraining for the methods filed beside it.

Filed under post-training › mid-training & continual pretraining