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
..
arch	Windows specific fixes (to-do: find libespeak-ng.dll automatically because it cannot be trusted to do it by default)	2024-11-03 19:19:15 -06:00
__init__.py	UGH	2024-11-05 22:13:58 -06:00
ar_nar.py	'borrowed' a sampling scheduler for NAR-len's RVQ level 0 (better than before, but still not good enough)	2024-11-07 21:19:14 -06:00
ar.py	I guess I'll fall for the NAR-len meme again (I don't know where my previous weights are, so I need to train it again to test something)	2024-11-06 19:17:12 -06:00
base.py	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
experimental.py	moved prints to use logger, edited readme (fused_attn doesnt seem stable for training)	2024-08-29 13:27:16 -05:00
lora.py	naive model offloading support (handles automatically splitting parts of the model to requested device per memory constraints, either inferred or requested in the yaml, input tensors are automatically migrated to the right device, it SEEMS to work for training under the test trainer when split between GPU and CPU) (this was specifically only because that Flux imagegen model released so I can test it there)	2024-08-01 20:12:06 -05:00
nar.py	I forgot about the time embedding...	2024-11-08 22:46:26 -06:00