fine tuning for simple binary classification task??

HI and thanks for Great library ;))

I see that it is not ready for tuning on binary or multilabels task without manually add a linear layer on top of model and implement the binary cross entropy loss,... right? or i'm in wrong?

The issue does not name a file, test, or entry point. First clarify whether binary and multilabel fine-tuning should be supported directly and what API and loss behavior are expected; done would be an agreed implementation scope with tests for the requested tasks.

Written by the indexing model from the issue text.