when x_i is large, torch.exp(x_i) will overflow.
In your implementation, x_i = x_i - x_max. So the softmax one equation should be exp(x_i - x_max) / (1 + sum(exp(x_i - x_max)) ?
kyegomez / AttentionIsOFFByOne
Implementation of "Attention Is Off By One" by Evan Miller
181
Contributors get 40% of received funds after fees
How does funding with Polar work?
1
Pay now to fund the work behind this issue.
2
Get updates on progress being made.
3
Maintainer is rewarded once the issue is completed.
FAQ
Backer
You're funding impactful open source efforts
Contributor
You want to contribute to this effort
Maintainer
You want to get funding like this too