mrq 2808f881c8 cleaned up subjugated audio embedding into a flag, flag can also have it include the original, underlying embedding as well (it seems to do better when set to inclusive)		2024-06-29 21:46:35 -05:00
..
arch	mamba2-hf using vasqu/mamba2-torch because it lets me use mamba2 without triton ops (training with my 4xV100s are not happy with mamba2 because of triton)	2024-06-14 19:42:17 -05:00
__init__.py	ugh	2024-06-11 23:59:28 -05:00
ar_nar.py	cleaned up subjugated audio embedding into a flag, flag can also have it include the original, underlying embedding as well (it seems to do better when set to inclusive)	2024-06-29 21:46:35 -05:00
base.py	cleaned up subjugated audio embedding into a flag, flag can also have it include the original, underlying embedding as well (it seems to do better when set to inclusive)	2024-06-29 21:46:35 -05:00
experimental.py	actually going for the suggested "2x layers, no intermediate scaling" is wrong for VALL-E, directly copying the normal transformer structure fixes mamba2 performance in the test trainer	2024-06-13 20:08:22 -05:00
lora.py	load exported LoRA weights if exists (to-do: make a better LoRA loading mechanism)	2024-06-18 21:45:46 -05:00
nar.py	the NAR only dream is dead (it just won't work)	2024-06-12 19:49:47 -05:00