mrq caad99ab78 fix for bsz>1 because I forgot the old implementation implicitly handles this		2025-04-02 17:17:37 -05:00
..
arch	tweaks	2025-03-28 19:49:54 -05:00
__init__.py
ar_nar_v2.py	is this my last cope (falling back to explicit duration prediction, as this regression just won't go away) (also the smaller model was lobotomized because of my ROCm setup having a botched SDPA for who knows why)	2025-04-02 17:01:24 -05:00
ar_nar.py
base_v2.py	fix for bsz>1 because I forgot the old implementation implicitly handles this	2025-04-02 17:17:37 -05:00
base.py
lora.py