rish-16 / aft-pytorch
Unofficial PyTorch implementation of Attention Free Transformer (AFT) layers by Apple Inc.
☆234Updated 2 years ago
Alternatives and similar repositories for aft-pytorch:
Users that are interested in aft-pytorch are comparing it to the libraries listed below
- Official PyTorch Implementation of Long-Short Transformer (NeurIPS 2021).☆225Updated 2 years ago
- Fully featured implementation of Routing Transformer☆291Updated 3 years ago
- Unofficial implementation of Google's FNet: Mixing Tokens with Fourier Transforms☆259Updated 3 years ago
- Implementation of gMLP, an all-MLP replacement for Transformers, in Pytorch☆424Updated 3 years ago
- Implementation of Linformer for Pytorch☆274Updated last year
- Is the attention layer even necessary? (https://arxiv.org/abs/2105.02723)☆483Updated 3 years ago
- Implementation of H-Transformer-1D, Hierarchical Attention for Sequence Learning☆160Updated last year
- Implementation of ResMLP, an all MLP solution to image classification, in Pytorch☆197Updated 2 years ago
- DeLighT: Very Deep and Light-Weight Transformers☆468Updated 4 years ago
- Implementation of Fast Transformer in Pytorch☆173Updated 3 years ago
- Implementation of the Transformer variant proposed in "Transformer Quality in Linear Time"☆360Updated last year
- Sequence modeling with Mega.☆295Updated 2 years ago
- Implementation of Long-Short Transformer, combining local and global inductive biases for attention over long sequences, in Pytorch☆118Updated 3 years ago
- Implementation of fused cosine similarity attention in the same style as Flash Attention☆211Updated 2 years ago
- My take on a practical implementation of Linformer for Pytorch.☆413Updated 2 years ago
- Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention☆260Updated 3 years ago
- Collection of the latest, greatest, deep learning optimizers (for Pytorch) - CNN, NLP suitable☆212Updated 3 years ago
- A simple and working implementation of Electra, the fastest way to pretrain language models from scratch, in Pytorch☆224Updated 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
- Transformer based on a variant of attention that is linear complexity in respect to sequence length☆751Updated 10 months ago
- Pytorch implementation of Compressive Transformers, from Deepmind☆156Updated 3 years ago
- Unofficial PyTorch implementation of Fastformer based on paper "Fastformer: Additive Attention Can Be All You Need"."☆134Updated 3 years ago
- Understanding the Difficulty of Training Transformers☆328Updated 2 years ago
- ☆376Updated last year
- Implementation of Feedback Transformer in Pytorch☆105Updated 4 years ago
- Code repository of the paper "Modelling Long Range Dependencies in ND: From Task-Specific to a General Purpose CNN" https://arxiv.org/abs…☆183Updated 2 years ago
- An implementation of local windowed attention for language modeling☆429Updated 2 months ago
- Implementation of Transformer in Transformer, pixel level attention paired with patch level attention for image classification, in Pytorc…☆304Updated 3 years ago
- PyTorch Implementation of OpenAI's Image GPT☆254Updated last year
- An All-MLP solution for Vision, from Google AI☆1,015Updated 6 months ago