axon
axon copied to clipboard
Add attention layers
We should work out a common API and implementation for working with attention layers. Right now they are easily implemented as custom layers, but we should have conveniences to save user's time
Can I take this on?
Yes, definitely! Let me know if you run into any issues or have questions
See https://github.com/elixir-nx/bumblebee
Maybe later it will make sense to move those attention implementations but for now it's okay :)