I understand that the way to add a new token and assign values to its embedding is possible with
That would correspond to updating the weight for the token of the final layer.
Is it possible to assign new weights for the needed token for other layers in a similar fashion?
We can access the weights for the deeper layers when passing
But these weights are not stored in a stay_dict like the weights of
the final layer stored in look-up matrix in
I am not sure what am I missing here?