mrq 9564ecda43 wrapper attention class for other sdpa backends + xformers seems to have broke...		2024-08-03 15:12:11 -05:00
..
arch	wrapper attention class for other sdpa backends + xformers seems to have broke...	2024-08-03 15:12:11 -05:00
__init__.py
ar_nar.py	fixes, throw an exception when using NAR only model with non-unified position IDs, since for some reason it outputs garbage for the NAR	2024-08-02 22:25:49 -05:00
base.py	wrapper attention class for other sdpa backends + xformers seems to have broke...	2024-08-03 15:12:11 -05:00
experimental.py
lora.py
nar.py	tweaks for the NAR-len model, maybe	2024-08-03 08:40:39 -05:00