mrq d12877ee09 added option to set probability of selecting the AR during training under a monolithic AR+NAR, added some more to-dos while I have them in mind		2023-10-02 16:52:42 -05:00
..
__init__.py	added option to use SGD optimizer through the YAML, added option to pass in additional optimizer parameters through the YAML, added experimental unified AR+NAR model (does not seem fruitful in testing)	2023-09-06 18:58:35 -05:00
adaln.py	Tweaks	2023-08-02 22:06:39 +00:00
ar_nar.py	added option to set probability of selecting the AR during training under a monolithic AR+NAR, added some more to-dos while I have them in mind	2023-10-02 16:52:42 -05:00
ar.py	restructured some things with the model to remove dead weights	2023-09-20 19:10:59 -05:00
base.py	restructured some things with the model to remove dead weights	2023-09-20 19:10:59 -05:00
nar.py	restructured some things with the model to remove dead weights	2023-09-20 19:10:59 -05:00
retnet.py	restructured some things with the model to remove dead weights	2023-09-20 19:10:59 -05:00
transformer.py	added ability to disable activation checkpointing through the YAML (it is very VRAM intensive at double layer size)	2023-09-05 15:38:21 -05:00