mlpen / Nystromformer
☆367Updated last year
Alternatives and similar repositories for Nystromformer:
Users that are interested in Nystromformer are comparing it to the libraries listed below
- Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention☆256Updated 3 years ago
- Implementation of Nyström Self-attention, from the paper Nyströmformer☆124Updated 11 months ago
- Fully featured implementation of Routing Transformer☆288Updated 3 years ago
- Fast Block Sparse Matrices for Pytorch☆547Updated 3 years ago
- Official PyTorch Implementation of Long-Short Transformer (NeurIPS 2021).☆226Updated 2 years ago
- Transformer based on a variant of attention that is linear complexity in respect to sequence length☆724Updated 8 months ago
- Simple and efficient RevNet-Library for PyTorch with XLA and DeepSpeed support and parameter offload☆125Updated 2 years ago
- Long Range Arena for Benchmarking Efficient Transformers☆739Updated last year
- Drop-in replacement for any ResNet with a significantly reduced memory footprint and better representation capabilities☆209Updated 8 months ago
- Implementation of Linformer for Pytorch☆262Updated last year
- Official code repository of the paper Linear Transformers Are Secretly Fast Weight Programmers.☆101Updated 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
- Is the attention layer even necessary? (https://arxiv.org/abs/2105.02723)☆483Updated 3 years ago
- ☆164Updated last year
- Understanding the Difficulty of Training Transformers☆327Updated 2 years ago
- The entmax mapping and its loss, a family of sparse softmax alternatives.☆419Updated 6 months ago
- Library for 8-bit optimizers and quantization routines.☆717Updated 2 years ago
- PyTorch dataset extended with map, cache etc. (tensorflow.data like)☆328Updated 2 years ago
- Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions☆257Updated last year
- Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"☆370Updated last year
- Approximate nearest neighbor search with product quantization on GPU in pytorch and cuda☆216Updated last year
- Implementation of H-Transformer-1D, Hierarchical Attention for Sequence Learning☆157Updated 11 months ago
- Unofficial PyTorch implementation of Attention Free Transformer (AFT) layers by Apple Inc.☆232Updated 2 years ago
- Trains Transformer model variants. Data isn't shuffled between batches.☆139Updated 2 years ago
- An attempt at the implementation of Glom, Geoffrey Hinton's new idea that integrates concepts from neural fields, top-down-bottom-up proc…☆193Updated 3 years ago
- VQVAEs, GumbelSoftmaxes and friends☆548Updated 3 years ago
- A PyTorch implementation of Perceiver, Perceiver IO and Perceiver AR with PyTorch Lightning scripts for distributed training☆446Updated last year
- End-to-end training of sparse deep neural networks with little-to-no performance loss.☆317Updated last year
- Sequence modeling with Mega.☆297Updated last year
- An implementation of Performer, a linear attention-based transformer, in Pytorch☆1,110Updated 2 years ago