mrq 0e995dbf2c is this my last cope (falling back to explicit duration prediction, as this regression just won't go away) (also the smaller model was lobotomized because of my ROCm setup having a botched SDPA for who knows why)		2025-04-02 17:01:24 -05:00
..
arch	tweaks	2025-03-28 19:49:54 -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	is this my last cope (falling back to explicit duration prediction, as this regression just won't go away) (also the smaller model was lobotomized because of my ROCm setup having a botched SDPA for who knows why)	2025-04-02 17:01:24 -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	is this my last cope (falling back to explicit duration prediction, as this regression just won't go away) (also the smaller model was lobotomized because of my ROCm setup having a botched SDPA for who knows why)	2025-04-02 17:01:24 -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