lucidrains / local-attention
An implementation of local windowed attention for language modeling
☆384Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for local-attention
- Implementation of Linformer for Pytorch☆257Updated 10 months ago
- Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch☆571Updated last week
- Transformer based on a variant of attention that is linear complexity in respect to sequence length☆698Updated 6 months ago
- Official PyTorch Implementation of Long-Short Transformer (NeurIPS 2021).☆222Updated 2 years ago
- Sequence modeling with Mega.☆298Updated last year
- Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"☆360Updated last year
- Fully featured implementation of Routing Transformer☆284Updated 3 years ago
- Implementation of the Transformer variant proposed in "Transformer Quality in Linear Time"☆350Updated last year
- Implementation of Mega, the Single-head Attention with Multi-headed EMA architecture that currently holds SOTA on Long Range Arena☆203Updated last year
- Approximate nearest neighbor search with product quantization on GPU in pytorch and cuda☆214Updated 11 months ago
- Implementation of fused cosine similarity attention in the same style as Flash Attention☆207Updated last year
- Code for the ALiBi method for transformer language models (ICLR 2022)☆507Updated last year
- [ICLR 2022] Official implementation of cosformer-attention in cosFormer: Rethinking Softmax in Attention☆179Updated last year
- Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention☆253Updated 3 years ago
- ☆164Updated last year
- Implementation of H-Transformer-1D, Hierarchical Attention for Sequence Learning☆155Updated 9 months ago
- My take on a practical implementation of Linformer for Pytorch.☆407Updated 2 years ago
- An implementation of Performer, a linear attention-based transformer, in Pytorch☆1,098Updated 2 years ago
- Implementation of Block Recurrent Transformer - Pytorch☆213Updated 3 months ago
- Implementation of Bit Diffusion, Hinton's group's attempt at discrete denoising diffusion, in Pytorch☆333Updated last year
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆293Updated 5 months ago
- A simple way to keep track of an Exponential Moving Average (EMA) version of your Pytorch model☆517Updated last month
- A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models☆642Updated last year
- An implementation of masked language modeling for Pytorch, made as concise and simple as possible☆177Updated last year
- Unofficial implementation of Google's FNet: Mixing Tokens with Fourier Transforms☆251Updated 3 years ago
- Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch☆225Updated 2 months ago
- A simple cross attention that updates both the source and target in one step☆152Updated 6 months ago
- A PyTorch implementation of Perceiver, Perceiver IO and Perceiver AR with PyTorch Lightning scripts for distributed training☆437Updated 10 months ago
- Long Range Arena for Benchmarking Efficient Transformers☆729Updated 11 months ago
- VQVAEs, GumbelSoftmaxes and friends☆535Updated 3 years ago