Change model output format to bundle relevant info for model application.

[tkkuehn]

To run the model application correctly, right now you need to both know and accurately input:

• The feature offsets used to train the model (via a feature_offsets.npz)
• The padding, size, and sampling rate (directly via CLI parameters)

I think it would be a big QoL improvement to bundle the feature offsets file and other three parameters (via a YAML or TOML file of some sort) with the model outputs. We could then zip them up with the model outputs (with a custom extension like .afidsregrf), so the end user just has to provide the one file to apply.py to correctly apply their model.