mrq 90b3509404 I'll just cope and say I cannot apply segmented attention masks to the smaller model as it's too trained on not doing it, and the regression came from dumb python aliasing rules		2025-03-27 13:27:51 -05:00
..
arch	I'll just cope and say I cannot apply segmented attention masks to the smaller model as it's too trained on not doing it, and the regression came from dumb python aliasing rules	2025-03-27 13:27:51 -05:00
__init__.py	nothing could go wrong part 2 (reverted and rewrote commits since there was a nasty regression)	2025-03-25 23:06:16 -05:00
ar_nar_v2.py	cannot get segmented mask to actually work without gradients exploding (need to find a different way to do duration prediction...)	2025-03-27 00:51:41 -05:00
ar_nar.py	nothing could go wrong part 2 (reverted and rewrote commits since there was a nasty regression)	2025-03-25 23:06:16 -05:00
base_v2.py	I'll just cope and say I cannot apply segmented attention masks to the smaller model as it's too trained on not doing it, and the regression came from dumb python aliasing rules	2025-03-27 13:27:51 -05:00
base.py	nothing could go wrong part 2 (reverted and rewrote commits since there was a nasty regression)	2025-03-25 23:06:16 -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