andrewgcodes / xlstm

my attempts at implementing various bits of Sepp Hochreiter's new xLSTM architecture
MIT License
111 stars 8 forks source link

xlstm

my attempts at implementing various bits of Sepp Hochreiter's new xLSTM architecture very oversimplified and probably somewhat wrong! please open PRs and make it better.

mLSTM: https://github.com/andrewgcodes/xlstm/blob/main/mLSTM.ipynb

Open In Colab