Pinned Loading

1. nanoUL2 nanoUL2 Public

   Forked from karpathy/nanoGPT

   A simple repository for training decoder-only UL2 models.

   Python

2. triton-prefix-lm-flash-attn triton-prefix-lm-flash-attn Public

   FlashAttention for prefix language modeling written in Triton

   Python 1

3. mechanistic-interpretability mechanistic-interpretability Public

   A toolbox for facilitating mechanistic interpretability research on small models and toy tasks.

   Python 2

4. minGPT-lightning minGPT-lightning Public

   Forked from karpathy/minGPT

   A modification of karpathy's minGPT to use PyTorch Lightning + Hydra

   Python

5. c3d c3d Public

   C3D for Keras (only Tensorflow backend at the moment) with easy preprocessing and automatic downloading of TF format sports1M weights

   Python 34 12

6. resnet152 resnet152 Public

   Adaptation of ResNet-152 to match Keras API with added large input option

   Python 27 10