Do all variations of the model need to have the same architecture?
Or can they be different types of models with different number of layers, etc?
Or can they be different types of models with different number of layers, etc?
That being said, there is some smart caching / hashing on layers such that if you do have models that are similar (i.e. a fine-tuned model where only some layers are fine-tuned), it'll minimize storage and transfer by reusing those weights.