mrq 67a6009555 (finally) added parallel AR for cfg.model.version >= 7 (nvidia/audio-codec-44khz is being a pain and it might require training purely AR first......)		2025-02-23 08:31:03 -06:00
..
arch	agony	2025-02-12 00:18:24 -06:00
__init__.py		2024-12-26 21:42:17 -06:00
ar_nar.py	(finally) added parallel AR for cfg.model.version >= 7 (nvidia/audio-codec-44khz is being a pain and it might require training purely AR first......)	2025-02-23 08:31:03 -06:00
base.py	fixes fixes fixes (a quarter of my recently processed audio returned zero'd tensors......)	2025-02-22 09:07:33 -06:00
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