epfml / collaborative-attention
Code for Multi-Head Attention: Collaborate Instead of Concatenate
☆150Updated last year
Related projects ⓘ
Alternatives and complementary repositories for collaborative-attention
- ☆212Updated 4 years ago
- Fully featured implementation of Routing Transformer☆284Updated 3 years ago
- A PyTorch implementation of the paper - "Synthesizer: Rethinking Self-Attention in Transformer Models"☆71Updated last year
- Implementation of Memformer, a Memory-augmented Transformer, in Pytorch☆106Updated 3 years ago
- [ICML 2020] code for "PowerNorm: Rethinking Batch Normalization in Transformers" https://arxiv.org/abs/2003.07845☆119Updated 3 years ago
- Implementation of Mixout with PyTorch☆74Updated last year
- Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention☆253Updated 3 years ago
- [ICML 2021 Oral] We show pure attention suffers rank collapse, and how different mechanisms combat it.☆161Updated 3 years ago
- Unofficial PyTorch implementation of Fastformer based on paper "Fastformer: Additive Attention Can Be All You Need"."☆134Updated 3 years ago
- This repository contains the code for running the character-level Sandwich Transformers from our ACL 2020 paper on Improving Transformer …☆55Updated 3 years ago
- ☆63Updated 2 years ago
- The official repository for our paper "The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers". We s…☆66Updated last year
- Understanding the Difficulty of Training Transformers☆326Updated 2 years ago
- Official PyTorch Implementation of Long-Short Transformer (NeurIPS 2021).☆222Updated 2 years ago
- Implementation of Feedback Transformer in Pytorch☆104Updated 3 years ago
- Cascaded Text Generation with Markov Transformers☆128Updated last year
- The entmax mapping and its loss, a family of sparse softmax alternatives.☆415Updated 4 months ago
- Pytorch implementation of Compressive Transformers, from Deepmind☆157Updated 3 years ago
- Official Pytorch Implementation of Length-Adaptive Transformer (ACL 2021)☆100Updated 4 years ago
- Implementation of Long-Short Transformer, combining local and global inductive biases for attention over long sequences, in Pytorch☆116Updated 3 years ago
- Code for the paper "Are Sixteen Heads Really Better than One?"☆168Updated 4 years ago
- Code for the ICML'20 paper "Improving Transformer Optimization Through Better Initialization"☆89Updated 3 years ago
- A 🤗-style implementation of BERT using lambda layers instead of self-attention☆70Updated 4 years ago
- A PyTorch implementation of the Transformer model from "Attention Is All You Need".☆59Updated 5 years ago
- Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr\"om Method (NeurIPS 2021)☆59Updated 2 years ago
- Code for EMNLP 2019 paper "Attention is not not Explanation"☆57Updated 3 years ago
- Code for the Shortformer model, from the ACL 2021 paper by Ofir Press, Noah A. Smith and Mike Lewis.☆145Updated 3 years ago
- Implementation of Sparsemax activation in Pytorch☆155Updated 4 years ago
- Official code repository of the paper Linear Transformers Are Secretly Fast Weight Programmers.☆99Updated 3 years ago
- NeurIPS 2019 - Learning Data Manipulation for Augmentation and Weighting☆109Updated 4 years ago