About the usage of depth
in the class MambaTransformerblock
, in model.py
#8
Labels
depth
in the class MambaTransformerblock
, in model.py
#8
Dear @kyegomez,
First of all, excuse me for my awkward English.
In
forward()
, I think usingzip
impliesdepth == transformer_depth == mamba_depth
.Hence, instead of using
transformer_depth
andmamba_depth
, how about to usedepth
?Would you mind if considering this idea?
Thank you very much.
The text was updated successfully, but these errors were encountered: