One day I had the crazy idea to try two non-mainstream things out at the same time. On top of that I figured I'd combine them in the same project, imagine that!
In this post I walk through Self-Attention Transformers from scratch with demos at the end for Text Classification & Generation, where the PyTorch-code is wrapped by fast.ai to simplify end-2-end.
In this post I improve the previous FAQ search engine by some low hanging fruits. The requirements stay the same thus SotA is not achieved but rather it's simply generic & easy on hardware (Raspberry Pi capable).