[ot][spam][crazy] adapters for semibalanced trees?

[Undiscussed Horrific Abuse, One Victim of Many]

long story short, from https://arxiv.org/pdf/2112.07916.pdf ,
transient global attention is a new approach to attention invented for
longt5, which appears to reliably outperform local attention in the
same architecture

the appearance of that, combined with finetunings i saw on the
huggingface hub using tglobal attention, seems enough reason to try to
use the tglobal models without fully understanding things in the
moment