mrq 2ccf1b5740 actually do duration prediction		2025-03-11 22:14:54 -05:00
..
arch	len prediction for new model (and remove logit normalization since it kills inferencing)	2025-03-11 20:33:09 -05:00
__init__.py	segregated experimental changes into its own streamlined file to avoid breaking the existing model, and it can pivot to the cleaned up code if it actually works (nothing is working)	2025-02-26 21:26:13 -06:00
ar_nar_v2.py	len prediction for new model (and remove logit normalization since it kills inferencing)	2025-03-11 20:33:09 -05:00
ar_nar.py	a gorillionth time's the charm (aka: the encoder/decoder pill is a tough pill to swallow)	2025-02-28 17:56:50 -06:00
base_v2.py	actually do duration prediction	2025-03-11 22:14:54 -05:00
base.py	fix attention backend not being used	2025-02-27 21:38:38 -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