Alternatives and similar repositories for linformer:

Users that are interested in linformer are comparing it to the libraries listed below

• lucidrains / linear-attention-transformer
  Transformer based on a variant of attention that is linear complexity in respect to sequence length
  ☆738Updated 9 months ago
• NVIDIA / transformer-ls
  Official PyTorch Implementation of Long-Short Transformer (NeurIPS 2021).
  ☆226Updated 2 years ago
• lucidrains / local-attention
  An implementation of local windowed attention for language modeling
  ☆420Updated last month
• lucidrains / routing-transformer
  Fully featured implementation of Routing Transformer
  ☆288Updated 3 years ago
• lucidrains / memory-efficient-attention-pytorch
  Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"
  ☆370Updated last year
• tatp22 / linformer-pytorch
  My take on a practical implementation of Linformer for Pytorch.
  ☆411Updated 2 years ago
• OpenNLPLab / cosFormer
  [ICLR 2022] Official implementation of cosformer-attention in cosFormer: Rethinking Softmax in Attention
  ☆185Updated 2 years ago
• lucidrains / FLASH-pytorch
  Implementation of the Transformer variant proposed in "Transformer Quality in Linear Time"
  ☆358Updated last year
• lucidrains / rotary-embedding-torch
  Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch
  ☆635Updated 2 months ago
• lucidrains / sinkhorn-transformer
  Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention
  ☆257Updated 3 years ago
• lucidrains / performer-pytorch
  An implementation of Performer, a linear attention-based transformer, in Pytorch
  ☆1,115Updated 3 years ago
• cmsflash / efficient-attention
  An implementation of the efficient attention module.
  ☆301Updated 4 years ago
• rishikksh20 / FNet-pytorch
  Unofficial implementation of Google's FNet: Mixing Tokens with Fourier Transforms
  ☆258Updated 3 years ago
• rish-16 / aft-pytorch
  Unofficial PyTorch implementation of Attention Free Transformer (AFT) layers by Apple Inc.
  ☆233Updated 2 years ago
• lucidrains / flash-cosine-sim-attention
  Implementation of fused cosine similarity attention in the same style as Flash Attention
  ☆210Updated 2 years ago
• lucidrains / fast-transformer-pytorch
  Implementation of Fast Transformer in Pytorch
  ☆172Updated 3 years ago
• lucidrains / long-short-transformer
  Implementation of Long-Short Transformer, combining local and global inductive biases for attention over long sequences, in Pytorch
  ☆118Updated 3 years ago
• lucidrains / nystrom-attention
  Implementation of Nyström Self-attention, from the paper Nyströmformer
  ☆127Updated last year
• rishikksh20 / MLP-Mixer-pytorch
  Unofficial implementation of MLP-Mixer: An all-MLP Architecture for Vision
  ☆217Updated 3 years ago
• lucidrains / memformer
  Implementation of Memformer, a Memory-augmented Transformer, in Pytorch
  ☆111Updated 4 years ago
• ctlllll / SGConv
  ☆163Updated 2 years ago
• lucidrains / axial-attention
  Implementation of Axial attention - attending to multi-dimensional data efficiently
  ☆371Updated 3 years ago
• facebookresearch / mega
  Sequence modeling with Mega.
  ☆298Updated 2 years ago
• lucidrains / mixture-of-experts
  A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models
  ☆692Updated last year
• mlpen / Nystromformer
  ☆371Updated last year
• 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
• lucidrains / bidirectional-cross-attention
  A simple cross attention that updates both the source and target in one step
  ☆162Updated 9 months ago
• lucidrains / compressive-transformer-pytorch
  Pytorch implementation of Compressive Transformers, from Deepmind
  ☆155Updated 3 years ago
• lucidrains / h-transformer-1d
  Implementation of H-Transformer-1D, Hierarchical Attention for Sequence Learning
  ☆160Updated last year
• fkodom / fft-conv-pytorch
  Implementation of 1D, 2D, and 3D FFT convolutions in PyTorch. Much faster than direct convolutions for large kernel sizes.
  ☆490Updated last year