mrq 98b357cc53 things i forgot to do last week now that some mental faculties were restored		2025-05-30 22:56:07 -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	allow defining the default model name through env var, register nemo-larger in the model name list thing	2025-05-21 16:50:59 -05:00
ar_nar_v2.py	things i forgot to do last week now that some mental faculties were restored	2025-05-30 22:56:07 -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