Create class to wrap first stages of sbi

[mstimberg]

This class should take parameters similarly to Fitter, and should wrap the first stages of the sbi process:

1. Sampling parameter combinations from the priors (simple uniform priors within the bounds as a first step)
2. Simulating the model on these parameter combinations
3. Extracting the metrics on the results
4. Training the inference network with the data

[mstimberg]

Closed via #49