Dashiell Stander dashstander

Pinned Loading

1. A Fast Fourier Transform over the symmetric group

   Python 4

2. Code and data for "Grokking Group Multiplication with Cosets" ICML 2024

   Jupyter Notebook 4

3. An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

   Python 7.4k 1.1k

4. A metric on the residual stream manifold of language models

   Python