* I have to add weight support for all regression function in the library

* needs testing + debugging

Pmulinka/auc - a small fix related to torchmetrics

Pmulinka/losses - all additional changes by @jrzaurin are ok

Fix some minor type and style issues. Adjusted the ZILN Loss so it works with former versions of pytorch and rename quantile regression multilabel label as qregression

Embedding, MC and draft requets

Fixed #60 and #61. Placing dropout in the right position and applying FullEmbeddingDropout only in training

need consultation, I am not sure if I got it correctly

added embedding rules, MonteCarlo(uncertainty) prediction and removed running of the tests on draf requests

Pmulinka/raytune