lucidrains / Mega-pytorch
Implementation of Mega, the Single-head Attention with Multi-headed EMA architecture that currently holds SOTA on Long Range Arena
☆204Updated last year
Alternatives and similar repositories for Mega-pytorch:
Users that are interested in Mega-pytorch are comparing it to the libraries listed below
- Implementation of Gated State Spaces, from the paper "Long Range Language Modeling via Gated State Spaces", in Pytorch☆97Updated last year
- Implementation of fused cosine similarity attention in the same style as Flash Attention☆210Updated 2 years ago
- Sequence modeling with Mega.☆298Updated 2 years ago
- Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch☆225Updated 5 months ago
- Sequence Modeling with Structured State Spaces☆62Updated 2 years ago
- Implementation of the Adan (ADAptive Nesterov momentum algorithm) Optimizer in Pytorch☆251Updated 2 years ago
- ☆163Updated 2 years ago
- Implementation of Discrete Key / Value Bottleneck, in Pytorch☆87Updated last year
- Implementation of Block Recurrent Transformer - Pytorch☆218Updated 5 months ago
- Implementation of Recurrent Interface Network (RIN), for highly efficient generation of images and video without cascading networks, in P…☆200Updated last year
- Memory Efficient Attention (O(sqrt(n)) for Jax and PyTorch☆180Updated 2 years ago
- Implementation of a Transformer that Ponders, using the scheme from the PonderNet paper☆80Updated 3 years ago
- Implementation of GateLoop Transformer in Pytorch and Jax☆87Updated 7 months ago
- Official PyTorch Implementation of Long-Short Transformer (NeurIPS 2021).☆226Updated 2 years ago
- Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"☆369Updated last year
- Implementation of Hourglass Transformer, in Pytorch, from Google and OpenAI☆84Updated 3 years ago
- Implementation of Long-Short Transformer, combining local and global inductive biases for attention over long sequences, in Pytorch☆118Updated 3 years ago
- Implementation of H-Transformer-1D, Hierarchical Attention for Sequence Learning☆159Updated last year
- Easy Hypernetworks in Pytorch and Jax☆97Updated 2 years ago
- A practical implementation of GradNorm, Gradient Normalization for Adaptive Loss Balancing, in Pytorch☆85Updated last year
- Sequence Modeling with Multiresolution Convolutional Memory (ICML 2023)☆122Updated last year
- ResiDual: Transformer with Dual Residual Connections, https://arxiv.org/abs/2304.14802☆93Updated last year
- Implementation of Memformer, a Memory-augmented Transformer, in Pytorch☆110Updated 4 years ago
- Explorations into the recently proposed Taylor Series Linear Attention☆92Updated 5 months ago
- Contrastive Language-Image Pretraining☆142Updated 2 years ago
- GPT, but made only out of MLPs☆88Updated 3 years ago
- Implementation of Fast Transformer in Pytorch☆172Updated 3 years ago
- Another attempt at a long-context / efficient transformer by me☆37Updated 2 years ago
- Implementation of Perceiver AR, Deepmind's new long-context attention network based on Perceiver architecture, in Pytorch☆86Updated last year
- Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT☆206Updated 5 months ago