Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Direct initialization of transformers using larger pretrained ones. Parent comment
We need something like this for "non-neural" things like transformers and normalization layers:
https://proceedings.mlr.press/v157/skorski21a/skorski21a.pdf
There are no comments on this comment yet.
We need something like this for "non-neural" things like transformers and normalization layers:
https://proceedings.mlr.press/v157/skorski21a/skorski21a.pdf