A question: Is it possible to use supervised-learn task to finetune embedding model?

nomic-ai / contrastors

Train Models Contrastively in Pytorch

Apache License 2.0

459 stars 35 forks source link

A question: Is it possible to use supervised-learn task to finetune embedding model? #35

Closed fengsxy closed 1 month ago

fengsxy commented 1 month ago

There is some work already shown when we use fintuned task, the embedding space will become a cluster. So if we have different information attention, could we use supervised task to train embedding?