Popular repositories Loading

1. mru-lm mru-lm Public

   An LM forked from my transformer-train-script repo that replaces attention with a novel idea called "matrix recurrent units."

   Python 4

2. nanoGPT-Experiment nanoGPT-Experiment Public

   Forked from karpathy/nanoGPT

   A fork of nanoGPT without layernorms and with a custom MLP

   Python 1

3. transformer-train-script transformer-train-script Public template

   Python 1