mrq 7feeb944a0 probably insane with even entertaining going this route		2024-06-03 20:26:27 -05:00
..
emb	DAC just doesn't work well enough......	2024-05-25 11:07:52 -05:00
engines	somehow between training sessions grad_norm = None even though it worked before	2024-06-02 08:29:27 -05:00
ext	backwards compat for old YAMLs with models, option to set flash attention 2 for Llama (and derivatives), included syncdoth/RetNets torchscale retnet for shits and grins, etc.	2024-04-16 10:02:31 -05:00
models	probably insane with even entertaining going this route	2024-06-03 20:26:27 -05:00
utils	reverted automatically disabling split loss calc, since it seems that it's actually cacling loss on prom causes the oddities, maybe	2024-06-01 12:34:59 -05:00
__init__.py
__main__.py	deprecate sole AR/NAR model by only keeping the AR+NAR (the beauty of no one using this is that I can break compat as much as I want), add tone token for when I classify my dataset with tone/emotion in the future, some other things	2024-04-15 19:54:32 -05:00
config.py	reverted automatically disabling split loss calc, since it seems that it's actually cacling loss on prom causes the oddities, maybe	2024-06-01 12:34:59 -05:00
data.py	ugh	2024-06-01 10:46:42 -05:00
export.py
inference.py	DAC just doesn't work well enough......	2024-05-25 11:07:52 -05:00
plot.py	deprecate sole AR/NAR model by only keeping the AR+NAR (the beauty of no one using this is that I can break compat as much as I want), add tone token for when I classify my dataset with tone/emotion in the future, some other things	2024-04-15 19:54:32 -05:00
samplers.py
train.py	nevermind it breaks training	2024-05-25 18:03:43 -05:00
webui.py	backwards compat for old YAMLs with models, option to set flash attention 2 for Llama (and derivatives), included syncdoth/RetNets torchscale retnet for shits and grins, etc.	2024-04-16 10:02:31 -05:00