lucidrains / sinkhorn-transformerLinks
Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention
☆268Updated 4 years ago
Alternatives and similar repositories for sinkhorn-transformer
Users that are interested in sinkhorn-transformer are comparing it to the libraries listed below
Sorting:
- Fully featured implementation of Routing Transformer☆296Updated 3 years ago
- Official PyTorch Implementation of Long-Short Transformer (NeurIPS 2021).☆228Updated 3 years ago
- Implementation of Sparsemax activation in Pytorch☆164Updated 5 years ago
- ☆383Updated 2 years ago
- [ICML 2021 Oral] We show pure attention suffers rank collapse, and how different mechanisms combat it.☆166Updated 4 years ago
- Approximate nearest neighbor search with product quantization on GPU in pytorch and cuda☆228Updated last year
- My take on a practical implementation of Linformer for Pytorch.☆421Updated 3 years ago
- Code for Multi-Head Attention: Collaborate Instead of Concatenate☆151Updated 2 years ago
- Implementation of https://arxiv.org/abs/1904.00962☆377Updated 4 years ago
- The entmax mapping and its loss, a family of sparse softmax alternatives.☆449Updated last year
- [ICML 2020] code for "PowerNorm: Rethinking Batch Normalization in Transformers" https://arxiv.org/abs/2003.07845☆120Updated 4 years ago
- Understanding the Difficulty of Training Transformers☆330Updated 3 years ago
- ☆219Updated 5 years ago
- DeLighT: Very Deep and Light-Weight Transformers☆468Updated 5 years ago
- Implementation of Linformer for Pytorch☆300Updated last year
- Efficient reservoir sampling implementation for PyTorch☆107Updated 4 years ago
- Pytorch implementation of Compressive Transformers, from Deepmind☆162Updated 4 years ago
- Implementation of gMLP, an all-MLP replacement for Transformers, in Pytorch☆430Updated 4 years ago
- Is the attention layer even necessary? (https://arxiv.org/abs/2105.02723)☆485Updated 4 years ago
- Official PyTorch Repo for "ReZero is All You Need: Fast Convergence at Large Depth"☆415Updated last year
- Transformer with Untied Positional Encoding (TUPE). Code of paper "Rethinking Positional Encoding in Language Pre-training". Improve exis…☆252Updated 3 years ago
- Code for the ICML'20 paper "Improving Transformer Optimization Through Better Initialization"☆89Updated 4 years ago
- Sequence modeling with Mega.☆300Updated 2 years ago
- Apollo: An Adaptive Parameter-wise Diagonal Quasi-Newton Method for Nonconvex Stochastic Optimization☆182Updated 3 years ago
- Official code repository of the paper Linear Transformers Are Secretly Fast Weight Programmers.☆105Updated 4 years ago
- Unofficial implementation of Google's FNet: Mixing Tokens with Fourier Transforms☆259Updated 4 years ago
- Implementation of Feedback Transformer in Pytorch☆108Updated 4 years ago
- Transformer based on a variant of attention that is linear complexity in respect to sequence length☆801Updated last year
- Implementation of H-Transformer-1D, Hierarchical Attention for Sequence Learning☆165Updated last year
- [ICLR 2022] Official implementation of cosformer-attention in cosFormer: Rethinking Softmax in Attention☆196Updated 2 years ago