NVIDIA / transformer-ls

Related projects ⓘ

Alternatives and complementary repositories for transformer-ls

• lucidrains / linformer
  Implementation of Linformer for Pytorch
  ☆257Updated 10 months ago
• lucidrains / long-short-transformer
  Implementation of Long-Short Transformer, combining local and global inductive biases for attention over long sequences, in Pytorch
  ☆116Updated 3 years ago
• OpenNLPLab / cosFormer
  [ICLR 2022] Official implementation of cosformer-attention in cosFormer: Rethinking Softmax in Attention
  ☆179Updated last year
• lucidrains / routing-transformer
  Fully featured implementation of Routing Transformer
  ☆284Updated 3 years ago
• lucidrains / flash-cosine-sim-attention
  Implementation of fused cosine similarity attention in the same style as Flash Attention
  ☆207Updated last year
• lucidrains / local-attention
  An implementation of local windowed attention for language modeling
  ☆384Updated 2 months ago
• facebookresearch / mega
  Sequence modeling with Mega.
  ☆298Updated last year
• lucidrains / sinkhorn-transformer
  Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention
  ☆253Updated 3 years ago
• lucidrains / fast-transformer-pytorch
  Implementation of Fast Transformer in Pytorch
  ☆171Updated 3 years ago
• google-research / diffstride
  TF/Keras code for DiffStride, a pooling layer with learnable strides.
  ☆124Updated 2 years ago
• rishikksh20 / FNet-pytorch
  Unofficial implementation of Google's FNet: Mixing Tokens with Fourier Transforms
  ☆251Updated 3 years ago
• lucidrains / Mega-pytorch
  Implementation of Mega, the Single-head Attention with Multi-headed EMA architecture that currently holds SOTA on Long Range Arena
  ☆203Updated last year
• rish-16 / aft-pytorch
  Unofficial PyTorch implementation of Attention Free Transformer (AFT) layers by Apple Inc.
  ☆228Updated 2 years ago
• microsoft / vision-longformer
  ☆241Updated 2 years ago
• epfml / collaborative-attention
  Code for Multi-Head Attention: Collaborate Instead of Concatenate
  ☆150Updated last year
• sIncerass / powernorm
  [ICML 2020] code for "PowerNorm: Rethinking Batch Normalization in Transformers" https://arxiv.org/abs/2003.07845
  ☆119Updated 3 years ago
• lucidrains / memformer
  Implementation of Memformer, a Memory-augmented Transformer, in Pytorch
  ☆106Updated 4 years ago
• lukemelas / do-you-even-need-attention
  Is the attention layer even necessary? (https://arxiv.org/abs/2105.02723)
  ☆480Updated 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"
  ☆360Updated last year
• LiyuanLucasLiu / Transformer-Clinic
  Understanding the Difficulty of Training Transformers
  ☆328Updated 2 years ago
• twistedcubic / attention-rank-collapse
  [ICML 2021 Oral] We show pure attention suffers rank collapse, and how different mechanisms combat it.
  ☆162Updated 3 years ago
• mlpen / Nystromformer
  ☆365Updated last year
• ctlllll / SGConv
  ☆164Updated last year
• lucidrains / FLASH-pytorch
  Implementation of the Transformer variant proposed in "Transformer Quality in Linear Time"
  ☆350Updated last year
• lucidrains / h-transformer-1d
  Implementation of H-Transformer-1D, Hierarchical Attention for Sequence Learning
  ☆155Updated 9 months ago
• lucidrains / linear-attention-transformer
  Transformer based on a variant of attention that is linear complexity in respect to sequence length
  ☆698Updated 6 months ago
• ischlag / fast-weight-transformers
  Official code repository of the paper Linear Transformers Are Secretly Fast Weight Programmers.
  ☆100Updated 3 years ago
• lucidrains / compressive-transformer-pytorch
  Pytorch implementation of Compressive Transformers, from Deepmind
  ☆157Updated 3 years ago
• tatp22 / linformer-pytorch
  My take on a practical implementation of Linformer for Pytorch.
  ☆407Updated 2 years ago
• ankandrew / online-label-smoothing-pt
  Implementation of Online Label Smoothing in PyTorch
  ☆94Updated 2 years ago