mrq 22ffaf3a33 have loss for the NAR not-ignore the text prompt, I imagine this should help the NAR and explain why it's always had a bit of an issue with training		2023-09-15 19:08:44 -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
ar_nar.py	added picking final candidate based on sum of score instead of first candidate (this changes nothing).	2023-09-13 13:19:11 -05:00
ar.py	added picking final candidate based on sum of score instead of first candidate (this changes nothing).	2023-09-13 13:19:11 -05:00
base.py	have loss for the NAR not-ignore the text prompt, I imagine this should help the NAR and explain why it's always had a bit of an issue with training	2023-09-15 19:08:44 -05:00
nar.py	implemented a naive beam search (I really should be taking a break)	2023-09-12 21:28:07 -05:00
retnet.py
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