mrq 9e27d2e02e huggingface zerogpu cringe		2025-04-16 15:25:45 -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	the culprit was initializing the level_weights for killing newly trained models.............	2025-04-10 23:06:16 -05:00
ar_nar.py	tweaks	2025-04-05 10:27:07 -05:00
base_v2.py	huggingface zerogpu cringe	2025-04-16 15:25:45 -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