allow distillable efficient vit to restore efficient vit as well

offer easy way to turn DistillableViT to ViT at the end of training

allow for overriding alpha as well on forward in distillation wrapper

no grad for teacher in distillation

add knowledge distillation with distillation tokens, in light of new …

…finding from facebook ai

allow for mean pool with efficient version too

offer a way to use mean pooling of last layer

fix the dimension per head to be independent of dim and heads, to mak…

…e sure users do not have it be too small to learn anything

simplify mlp head

remove float(-inf) as masking value