lucidrains / local-attention
An implementation of local windowed attention for language modeling
☆403Updated this week
Alternatives and similar repositories for local-attention:
Users that are interested in local-attention are comparing it to the libraries listed below
- Transformer based on a variant of attention that is linear complexity in respect to sequence length☆724Updated 8 months ago
- Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch☆609Updated last month
- Implementation of Linformer for Pytorch☆262Updated last year
- Official PyTorch Implementation of Long-Short Transformer (NeurIPS 2021).☆226Updated 2 years ago
- Sequence modeling with Mega.☆297Updated 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
- Fully featured implementation of Routing Transformer☆288Updated 3 years ago
- Implementation of the Transformer variant proposed in "Transformer Quality in Linear Time"☆357Updated last year
- ☆164Updated last year
- Implementation of Axial attention - attending to multi-dimensional data efficiently☆361Updated 3 years ago
- An implementation of Performer, a linear attention-based transformer, in Pytorch☆1,110Updated 2 years ago
- [ICLR 2022] Official implementation of cosformer-attention in cosFormer: Rethinking Softmax in Attention☆185Updated 2 years ago
- Code for the ALiBi method for transformer language models (ICLR 2022)☆510Updated last year
- Implementation of fused cosine similarity attention in the same style as Flash Attention☆210Updated last year
- ☆285Updated last month
- A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models☆668Updated last year
- Implementation of Mega, the Single-head Attention with Multi-headed EMA architecture that currently holds SOTA on Long Range Arena☆204Updated last year
- Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention☆256Updated 3 years ago
- Pytorch library for fast transformer implementations☆1,665Updated last year
- A PyTorch implementation of Perceiver, Perceiver IO and Perceiver AR with PyTorch Lightning scripts for distributed training☆446Updated last year
- Approximate nearest neighbor search with product quantization on GPU in pytorch and cuda☆216Updated last year
- A simple cross attention that updates both the source and target in one step☆161Updated 8 months ago
- Unofficial implementation of Google's FNet: Mixing Tokens with Fourier Transforms☆256Updated 3 years ago
- Implementation of Bit Diffusion, Hinton's group's attempt at discrete denoising diffusion, in Pytorch☆340Updated last year
- Implementation of https://srush.github.io/annotated-s4☆477Updated last year
- Implementation of Perceiver, General Perception with Iterative Attention, in Pytorch☆1,115Updated last year
- A simple way to keep track of an Exponential Moving Average (EMA) version of your Pytorch model☆548Updated last month
- Unofficial PyTorch implementation of Attention Free Transformer (AFT) layers by Apple Inc.☆232Updated 2 years ago
- Learning Rate Warmup in PyTorch☆399Updated this week
- An implementation of the efficient attention module.☆297Updated 4 years ago