mrq c690aa509d fixes and compat (MoE-fying an existing model and retraining from there just ruins it after a second of audio...)		2023-12-25 21:20:32 -06:00
..
__init__.py	experts weren't forwarded into constructer (wasted a few days of training garbage)	2023-12-23 16:08:17 -06:00
adaln.py
ar_nar.py	fixes and compat (MoE-fying an existing model and retraining from there just ruins it after a second of audio...)	2023-12-25 21:20:32 -06:00
ar.py	actually use langs from the dataloader	2023-10-11 21:21:50 -05:00
base.py	fixes and compat (MoE-fying an existing model and retraining from there just ruins it after a second of audio...)	2023-12-25 21:20:32 -06:00
nar.py	actually use langs from the dataloader	2023-10-11 21:21:50 -05:00
retnet.py
transformer.py