Lack of the deep_norm variants of transformer
ZegangC opened this issue · 1 comments
ZegangC commented
Hello, I used the "deep_norm" model with Xtransformer in the past, but after the update last week, it seems that Xtransformer no longer supports this model. Is there any intention to reintroduce it?
lucidrains commented
no, it will not be reintroduced