lucidrains / local-attention
An implementation of local windowed attention for language modeling
☆429Updated 2 months ago
Alternatives and similar repositories for local-attention:
Users that are interested in local-attention are comparing it to the libraries listed below
- Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch☆651Updated 3 months ago
- Implementation of Linformer for Pytorch☆274Updated last year
- Transformer based on a variant of attention that is linear complexity in respect to sequence length☆751Updated 10 months ago
- Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"☆372Updated last year
- Sequence modeling with Mega.☆295Updated 2 years ago
- Official PyTorch Implementation of Long-Short Transformer (NeurIPS 2021).☆225Updated 2 years ago
- Fully featured implementation of Routing Transformer☆289Updated 3 years ago
- Code for the ALiBi method for transformer language models (ICLR 2022)☆518Updated last year
- Implementation of the Transformer variant proposed in "Transformer Quality in Linear Time"☆360Updated last year
- An implementation of Performer, a linear attention-based transformer, in Pytorch☆1,116Updated 3 years ago
- A simple way to keep track of an Exponential Moving Average (EMA) version of your Pytorch model☆565Updated 3 months ago
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆321Updated 9 months ago
- Approximate nearest neighbor search with product quantization on GPU in pytorch and cuda☆220Updated last year
- Implementation of fused cosine similarity attention in the same style as Flash Attention☆211Updated 2 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
- Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention☆260Updated 3 years ago
- Pytorch library for fast transformer implementations☆1,687Updated 2 years ago
- My take on a practical implementation of Linformer for Pytorch.☆413Updated 2 years ago
- Implementation of Nyström Self-attention, from the paper Nyströmformer☆129Updated last year
- A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models☆714Updated last year
- A simple cross attention that updates both the source and target in one step☆164Updated 10 months ago
- Implementation of Block Recurrent Transformer - Pytorch☆218Updated 7 months ago
- Long Range Arena for Benchmarking Efficient Transformers☆748Updated last year
- [ICLR 2022] Official implementation of cosformer-attention in cosFormer: Rethinking Softmax in Attention☆188Updated 2 years ago
- Unofficial implementation of Google's FNet: Mixing Tokens with Fourier Transforms☆259Updated 3 years ago
- Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models☆781Updated 8 months ago
- Implementation of H-Transformer-1D, Hierarchical Attention for Sequence Learning☆160Updated last year
- Pytorch implementation of Compressive Transformers, from Deepmind☆156Updated 3 years ago
- Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch☆226Updated 6 months ago
- ☆376Updated last year