mrq 354f8e059d store dataset hash alongside state dict so it can be ignored if mismatched		2024-11-11 18:16:56 -06:00
..
emb	fixes	2024-11-10 20:37:50 -06:00
engines	fixes	2024-11-10 20:37:50 -06:00
ext
models	tweaks	2024-11-11 12:40:41 -06:00
utils	store dataset hash alongside state dict so it can be ignored if mismatched	2024-11-11 18:16:56 -06:00
__init__.py
__main__.py	all I can do now until I wait for the model to (re)train for pure NAR	2024-11-09 22:57:34 -06:00
config.py	use homwbrewed caching system for dataloader paths / durations (I'm pretty sure I am now triggering OOM killers with my entire dataset used)	2024-11-11 16:32:08 -06:00
data.py	store dataset hash alongside state dict so it can be ignored if mismatched	2024-11-11 18:16:56 -06:00
demo.py
export.py
inference.py	unified nar.py into ar_nar.py	2024-11-10 12:19:48 -06:00
plot.py
samplers.py	unified nar.py into ar_nar.py	2024-11-10 12:19:48 -06:00
train.py	dropped subtrain dataloader since its useless to duplicate	2024-11-11 17:00:49 -06:00
webui.py