erksch / fnet-pytorchLinks
Unofficial PyTorch implementation of Google's FNet: Mixing Tokens with Fourier Transforms. With checkpoints.
☆74Updated 2 years ago
Alternatives and similar repositories for fnet-pytorch
Users that are interested in fnet-pytorch are comparing it to the libraries listed below
Sorting:
- Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr\"om Method (NeurIPS 2021)☆61Updated 3 years ago
- Unofficial implementation of Google's FNet: Mixing Tokens with Fourier Transforms☆260Updated 4 years ago
- ☆163Updated 2 years ago
- Implementation of Memformer, a Memory-augmented Transformer, in Pytorch☆117Updated 4 years ago
- Implementation of Nyström Self-attention, from the paper Nyströmformer☆135Updated 2 months ago
- PyTorch implementation of FNet: Mixing Tokens with Fourier transforms☆27Updated 4 years ago
- Axial Positional Embedding for Pytorch☆81Updated 3 months ago
- Implementation of Long-Short Transformer, combining local and global inductive biases for attention over long sequences, in Pytorch☆119Updated 3 years ago
- Implementation of Mega, the Single-head Attention with Multi-headed EMA architecture that currently holds SOTA on Long Range Arena☆204Updated last year
- Implementation of Linformer for Pytorch☆286Updated last year
- Implementation of H-Transformer-1D, Hierarchical Attention for Sequence Learning☆161Updated last year
- Implementations of various linear RNN layers using pytorch and triton☆51Updated last year
- Code for the paper PermuteFormer☆42Updated 3 years ago
- Implementation of Fast Transformer in Pytorch☆174Updated 3 years ago
- Implementation of fused cosine similarity attention in the same style as Flash Attention☆214Updated 2 years ago
- Official PyTorch Implementation of Long-Short Transformer (NeurIPS 2021).☆225Updated 3 years ago
- Sequence Modeling with Structured State Spaces☆64Updated 2 years ago
- Implementation of Memory-Compressed Attention, from the paper "Generating Wikipedia By Summarizing Long Sequences"☆71Updated 2 years ago
- TF/Keras code for DiffStride, a pooling layer with learnable strides.☆124Updated 3 years ago
- Implementation of Gated State Spaces, from the paper "Long Range Language Modeling via Gated State Spaces", in Pytorch☆100Updated 2 years ago
- Transformers w/o Attention, based fully on MLPs☆93Updated last year
- Implementation of a Transformer using ReLA (Rectified Linear Attention) from https://arxiv.org/abs/2104.07012☆50Updated 3 years ago
- Implementation of Agent Attention in Pytorch☆90Updated 10 months ago
- Relative Positional Encoding for Transformers with Linear Complexity☆63Updated 3 years ago
- Another attempt at a long-context / efficient transformer by me☆38Updated 3 years ago
- Recent Advances in MLP-based Models (MLP is all you need!)☆115Updated 2 years ago
- Unofficial PyTorch implementation of the paper "cosFormer: Rethinking Softmax In Attention".☆44Updated 3 years ago
- PyTorch implementation of Soft MoE by Google Brain in "From Sparse to Soft Mixtures of Experts" (https://arxiv.org/pdf/2308.00951.pdf)☆73Updated last year
- Code repository for the ICLR 2022 paper "FlexConv: Continuous Kernel Convolutions With Differentiable Kernel Sizes" https://openreview.ne…☆115Updated 2 years ago
- ☆33Updated 4 years ago