mrq 83eab4fa59 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
..
arch	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
__init__.py
ar_nar.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
base.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
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
nar.py	the NAR only dream is dead (it just won't work)	2024-06-12 19:49:47 -05:00