Alternatives and similar repositories for cosFormer

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

• lucidrains / FLASH-pytorch
  Implementation of the Transformer variant proposed in "Transformer Quality in Linear Time"
  ☆366Updated last year
• NVIDIA / transformer-ls
  Official PyTorch Implementation of Long-Short Transformer (NeurIPS 2021).
  ☆225Updated 3 years ago
• twistedcubic / attention-rank-collapse
  [ICML 2021 Oral] We show pure attention suffers rank collapse, and how different mechanisms combat it.
  ☆165Updated 4 years ago
• lucidrains / linformer
  Implementation of Linformer for Pytorch
  ☆290Updated last year
• thuml / LogME
  Code release for "LogME: Practical Assessment of Pre-trained Models for Transfer Learning" (ICML 2021) and Ranking and Tuning Pre-trained…
  ☆208Updated last year
• kuixu / Linear-Multihead-Attention
  Reproducing the Linear Multihead Attention introduced in Linformer paper (Linformer: Self-Attention with Linear Complexity)
  ☆76Updated 5 years ago
• leaderj1001 / Synthesizer-Rethinking-Self-Attention-Transformer-Models
  Implementing SYNTHESIZER: Rethinking Self-Attention in Transformer Models using Pytorch
  ☆70Updated 5 years ago
• lucidrains / long-short-transformer
  Implementation of Long-Short Transformer, combining local and global inductive biases for attention over long sequences, in Pytorch
  ☆119Updated 3 years ago
• haofanwang / awesome-mlp-papers
  Recent Advances in MLP-based Models (MLP is all you need!)
  ☆115Updated 2 years ago
• sunxm2357 / AdaShare
  AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning
  ☆112Updated 4 years ago
• lucidrains / local-attention
  An implementation of local windowed attention for language modeling
  ☆460Updated 6 months ago
• lucidrains / sinkhorn-transformer
  Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention
  ☆265Updated 3 years ago
• evelinehong / Transformer_Relative_Position_PyTorch
  Implement the paper "Self-Attention with Relative Position Representations"
  ☆135Updated 4 years ago
• OpenNLPLab / Transnormer
  [EMNLP 2022] Official implementation of Transnormer in our EMNLP 2022 paper - The Devil in Linear Transformer
  ☆61Updated last year
• wuch15 / Fastformer
  A pytorch &keras implementation and demo of Fastformer.
  ☆189Updated 2 years ago
• facebookresearch / mega
  Sequence modeling with Mega.
  ☆296Updated 2 years ago
• BIGBALLON / distribuuuu
  The pure and clear PyTorch Distributed Training Framework.
  ☆276Updated last year
• rishikksh20 / FNet-pytorch
  Unofficial implementation of Google's FNet: Mixing Tokens with Fourier Transforms
  ☆259Updated 4 years ago
• cmsflash / efficient-attention
  An implementation of the efficient attention module.
  ☆319Updated 4 years ago
• xuanqing94 / FLOATER
  Learning to Encode Position for Transformer with Continuous Dynamical Model
  ☆60Updated 4 years ago
• lancopku / Explicit-Sparse-Transformer
  code for Explicit Sparse Transformer
  ☆62Updated last year
• rentainhe / pytorch-distributed-training
  Simple tutorials on Pytorch DDP training
  ☆281Updated 2 years ago
• sIncerass / powernorm
  [ICML 2020] code for "PowerNorm: Rethinking Batch Normalization in Transformers" https://arxiv.org/abs/2003.07845
  ☆120Updated 4 years ago
• Arnav0400 / ViT-Slim
  Official code for our CVPR'22 paper “Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space”
  ☆250Updated last year
• bzhangGo / rmsnorm
  Root Mean Square Layer Normalization
  ☆245Updated 2 years ago
• princeton-nlp / CoFiPruning
  [ACL 2022] Structured Pruning Learns Compact and Accurate Models https://arxiv.org/abs/2204.00408
  ☆196Updated 2 years ago
• HKUNLP / efficient-attention
  [EVA ICLR'23; LARA ICML'22] Efficient attention mechanisms via control variates, random features, and importance sampling
  ☆86Updated 2 years ago
• Junya-Chen / FlatCLR
  FlatNCE: A Novel Contrastive Representation Learning Objective
  ☆90Updated 3 years ago
• juntang-zhuang / GSAM
  PyTorch repository for ICLR 2022 paper (GSAM) which improves generalization (e.g. +3.8% top-1 accuracy on ImageNet with ViT-B/32)
  ☆143Updated 2 years ago
• thegregyang / LossUpAccUp
  Loss and accuracy go opposite ways...right?
  ☆94Updated 5 years ago