Kwargs propagation from _get_model in quantize_weights to MLModel in _get_model

[asafl]

When running quantize_weights with the weights_dir parameter, it doesn’t propagate to MLModel, resulting in: Exception: MLModel of type mlProgram cannot be loaded just from the model spec object. It also needs the path to the weights file. Please provide that as well, using the 'weights_dir' argument. Adding **kwargs in line 1691, in _get_model of the quantization_utils module, in the _get_model signature and in the return MLModel(spec, compute_units=compute_units, **kwargs) line fixes it.