Add auxiliary confidence head

[chrishokamp]

Goal: At some point during training, we wish to introduce an additional confidence head, which will output model confidence that a given prediction is correct.

• head can be trained on held-out or cross validation splits
• head loss can optionally backprop into model parameters, or can be detached from model params, and use static model representation

current loss computation https://github.com/jackboyla/GLiREL/blob/main/glirel/model.py#L242-L259 backprop: https://github.com/jackboyla/GLiREL/blob/main/glirel/model.py#L242-L259

[chrishokamp]

Note multiple heads can be trained for sub-objectives, for example just for the prompt representation https://github.com/jackboyla/GLiREL/blob/main/glirel/model.py#L64-L70 and encoding a prior probability that the trained model will succeed at predicting a given zero-shot relation

[q-chrishokamp]

Flair subtoken pooling magic https://github.com/flairNLP/flair/blob/a852bff2b8c3cab3dcf7bd19fb1c528225816bf6/flair/embeddings/transformer.py#L233-L239