Open Models Almanac
Methodspost-trainingmid-training & continual pretraining

single mention · post-training

Joint text-and-audio mid-training

Mid-training that unfreezes the model and trains on a mixture of text and audio datasets.

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