mrq 3337c69e5a leverage between xformers and torch.backends.cuda.sdp_kernel for attention		2024-05-11 17:14:05 -05:00
..
emb	oops	2024-05-09 22:33:40 -05:00
engines	remove redundant loss, tweak readme	2024-05-11 15:02:47 -05:00
ext
models	leverage between xformers and torch.backends.cuda.sdp_kernel for attention	2024-05-11 17:14:05 -05:00
utils	leverage between xformers and torch.backends.cuda.sdp_kernel for attention	2024-05-11 17:14:05 -05:00
__init__.py
__main__.py
config.py	leverage between xformers and torch.backends.cuda.sdp_kernel for attention	2024-05-11 17:14:05 -05:00
data.py	might just be better to explicitly define prompt duration ranges, especially under a "train small contexts then increase it" training paradigm	2024-05-11 09:50:54 -05:00
export.py
inference.py
plot.py
samplers.py
train.py
webui.py