Add ability to run models via __call__(), and not just using generate()

[jalammar]

Ecco currently only runs models using the generate() method. This makes it more geared towards GPT-like models. adding support to running models via call(), and collecting activations/saliency of that run would make it much useful. It opens the door towards supporting MLMs #6.

I am currently working on this in https://github.com/jalammar/ecco/tree/batch-input-activations