Closed NohTow closed 1 month ago
As discussed on discord, during the refactor, the intermediate_size of the GLU was cut in half, this PR set it back to its original definition for consistency. I also took the opportunity to fix some typos in the docstrings.
LGTM
ohallstrom
commented
1 month ago
As discussed on discord, during the refactor, the intermediate_size of the GLU was cut in half, this PR set it back to its original definition for consistency. I also took the opportunity to fix some typos in the docstrings.