Open Models Almanac
Methodspost-trainingsupervised fine-tuning

single mention · post-training

Cross-category integration of multilingual samples in SFT data

Distributes multilingual examples across most task categories in the SFT mixture.

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.

Filed under post-training › supervised fine-tuning