We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Tile primitives for speedy kernels
Cuda 1.9k 92
Convolutions for Sequence Modeling
Assembly 873 70
Official implementation for HyenaDNA, a long-range genomic foundation model built with Hyena
Assembly 620 87
Understand and test language model architectures on synthetic tasks.
FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores
Repo for "Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture"
Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"
Creative interactive views of any dataset.
Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"
Aioli: A unified optimization framework for language model data mixing
train with kittens!