How to train this?

Hi, I want to use this package to experiment with data different than images (multivariate time series).
I see that the `commitment_loss` that is returned is not a tensor, but rather a built in `float`, hence it's not possible to backprop through it.

For now i didn't modify any of my other loss calculation code, i just plugged in the quantizer at the beginning of my architecture, but i'd like to be sure if this is the correct way to go about this.

Thanks and keep up, you're doing god's work with your repositories!

Start by tracing the quantizer's commitment_loss return value and how the quantizer is inserted at the beginning of the architecture. Reproduce the multivariate time-series setup and verify whether the loss remains differentiable; done means establishing a supported training path or documenting the limitation.

Written by the indexing model from the issue text.