DeBERTa
DeBERTa copied to clipboard
[WIP] ONNX conversion
Changes needed to convert DeBerta to ONNX
Instead of change code every where, why not just change StableDropout?
Previous iterations i tried to redefine StableDropout to inherit from nn.Dropout, but it led to regression in model stats. Could not figure out why. If i do change this way there is no regression. Something was missing with just redefining StableDropout.