On my overleaf. It's a joke we made within my lab about all the recent xGLU variants of ffw that frankly should not change the results significantly. I now use it as a playground to test inserting emojis in papers 😉
Interestingly GluGlu activations are demonstrating significant gains on Winograd-like datasets, with performance curiously peaking as we approach the winter holiday period. 🍷 Inspired by this, we will release a new dataset called GluWine following the completion of extensive experimentation.
Comments