mrq b2b243e7e7 addresses #9		2025-05-05 13:03:44 -05:00
..
arch	diagnosed both hf/llama.cpp versions to probably just being a faulty export method (to-do: migrate vall_e.models.base to vall_e.export --hf)	2025-04-05 22:05:39 -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	addresses #9	2025-05-05 13:03:44 -05:00
ar_nar.py	addresses #9	2025-05-05 13:03:44 -05:00
base_v2.py	more notes / re-enabled top-k/p samplers for new implementation	2025-04-19 14:04:34 -05:00
base.py	diagnosed both hf/llama.cpp versions to probably just being a faulty export method (to-do: migrate vall_e.models.base to vall_e.export --hf)	2025-04-05 22:05:39 -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