gmongaras - Overview Skip to content Navigation Menu Pricing Provide feedback Saved searches Use saved searches to filter your results more quickly Sign up Appearance settings When softmax attention is sus Gabriel Mongaras gmongaras When softmax attention is sus Block or report gmongaras Pinned Loading A repo that attempts to train stable diffusion 3 from scratch Python 42 4 Code for the paper "2Mamba2Furious: Linear in complexity, competitive in accuracy" Jupyter Notebook 3 Code for the paper "Cottention: Linear Transformers With Cosine Attention" Cuda 20 Creating a waifu Jupyter Notebook 131 42 Public code for my protogen C 1