feat: Add multilabel classification for training

[Pringled]

This PR adds multilabel classification to the training module. If labels are passed as a list[list[str]], the model is automatically trained as a multilabel classification model.

[codecov]

Codecov Report

Attention: Patch coverage is 98.01980% with 2 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
model2vec/train/classifier.py	96.49%	2 Missing ⚠️

Files with missing lines	Coverage Δ
model2vec/inference/model.py	90.58% <100.00%> (+2.01%)	⬆️
tests/conftest.py	100.00% <100.00%> (ø)
tests/test_inference.py	100.00% <100.00%> (ø)
tests/test_trainable.py	100.00% <100.00%> (ø)
model2vec/train/classifier.py	97.31% <96.49%> (-0.10%)	⬇️