mrq 5fe01ffc6c more notes / re-enabled top-k/p samplers for new implementation		2025-04-19 14:04:34 -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	new implementation tweaks and fixes to make it actually better (there were a lot of badwrong things being done that harmed the output quality, will evaluate the model further)	2025-04-18 20:36:44 -05:00
ar_nar.py	when you uhh when you for once use your main rig to test and forgot to and when you port things back over	2025-04-18 20:49:00 -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