0.1.1

add a final norm to the latents after all the latent self attention

0.1.0

allow for one to set a greater dimension for the latent dimensions (d…

0.0.6

unweight tie layers, given feedback from author

0.0.5

add the PEG module from vit literature

0.0.3

use axial positional embedding, and make sure to always show gratitude

0.0.2

missing absolute positional embedding

0.0.1

complete first pass