mrq 69b0b3b854 set timestep tensor to whatever the time embedding's dtype is because it'll gripe under amp		2024-11-09 00:11:16 -06:00
..
emb
engines	new NAR-len training paradigm......	2024-11-07 11:32:11 -06:00
ext
models	set timestep tensor to whatever the time embedding's dtype is because it'll gripe under amp	2024-11-09 00:11:16 -06:00
utils
__init__.py
__main__.py
config.py
data.py
demo.py
export.py
inference.py	repeat extend the prom to fill the initial tokens for nar-len (it somewhat works, the model just needs to train more)	2024-11-06 23:29:53 -06:00
plot.py
samplers.py	I suppose I just have a shit training method since the sampler is as solid as I can get it...............	2024-11-08 22:05:41 -06:00
train.py
webui.py