mrq d343bde09b residual_in_fp32=False for mamba arch backends because it breaks the classifier (output projection / lm head / what-have-you) under AMP		2024-06-15 12:08:03 -05:00
..
arch
__init__.py
ar_nar.py
base.py	residual_in_fp32=False for mamba arch backends because it breaks the classifier (output projection / lm head / what-have-you) under AMP	2024-06-15 12:08:03 -05:00
experimental.py
nar.py