Open Models Almanac
Methodspost-trainingsupervised fine-tuning

specific method · filed under post-training

Multitask fine-tuning

Fine-tunes across multiple tasks, with evidence noting transfer gains in low-data settings.

The sources on this page name it without explaining how it works. The line above is the extraction's one-line gloss. See supervised fine-tuning for the methods filed beside it.

Also called Multitask fine-tuning across tasks, multitask finetuning, Multitask finetuning for task transfer.

sources
2
model
1
lab adopt it
1
strongest
used

Documented in

Hugging Face

Evidence

2 quotes from 2 sources, one card per model, each opening with its strongest.

How sources treat it
evaluated 1used 1
↑