epfml / collaborative-attention
Code for Multi-Head Attention: Collaborate Instead of Concatenate
☆152Updated last year
Alternatives and similar repositories for collaborative-attention:
Users that are interested in collaborative-attention are comparing it to the libraries listed below
- Fully featured implementation of Routing Transformer☆293Updated 3 years ago
- ☆218Updated 4 years ago
- Understanding the Difficulty of Training Transformers☆329Updated 2 years ago
- [ICML 2020] code for "PowerNorm: Rethinking Batch Normalization in Transformers" https://arxiv.org/abs/2003.07845☆119Updated 3 years ago
- ☆63Updated 2 years ago
- This repository contains the code for running the character-level Sandwich Transformers from our ACL 2020 paper on Improving Transformer …☆55Updated 4 years ago
- Implementation of Mixout with PyTorch☆75Updated 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
- Code for the ICML'20 paper "Improving Transformer Optimization Through Better Initialization"☆88Updated 4 years ago
- A PyTorch implementation of the paper - "Synthesizer: Rethinking Self-Attention in Transformer Models"☆73Updated 2 years ago
- Checking the interpretability of attention on text classification models☆48Updated 5 years ago
- Official PyTorch Implementation of Long-Short Transformer (NeurIPS 2021).☆225Updated 2 years ago
- Transformers without Tears: Improving the Normalization of Self-Attention☆131Updated 10 months ago
- Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention☆260Updated 3 years ago
- Language Model Baselines for PyTorch☆42Updated 4 years ago
- A 🤗-style implementation of BERT using lambda layers instead of self-attention☆69Updated 4 years ago
- FairSeq repo with Apollo optimizer☆114Updated last year
- Trains Transformer model variants. Data isn't shuffled between batches.☆141Updated 2 years ago
- A simple module consistently outperforms self-attention and Transformer model on main NMT datasets with SoTA performance.☆86Updated last year
- Code for EMNLP 2019 paper "Attention is not not Explanation"☆58Updated 3 years ago
- Code for the paper "Are Sixteen Heads Really Better than One?"☆171Updated 5 years ago
- Implementation of Feedback Transformer in Pytorch☆105Updated 4 years ago
- The official repository for our paper "The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers". We s…☆67Updated 2 years ago
- Cascaded Text Generation with Markov Transformers☆129Updated 2 years ago
- Official code repository of the paper Linear Transformers Are Secretly Fast Weight Programmers.☆104Updated 3 years ago
- [ICML 2021 Oral] We show pure attention suffers rank collapse, and how different mechanisms combat it.☆164Updated 4 years ago
- Official Pytorch Implementation of Length-Adaptive Transformer (ACL 2021)☆101Updated 4 years ago
- NeurIPS 2019 - Learning Data Manipulation for Augmentation and Weighting☆109Updated 4 years ago
- ☆64Updated 5 years ago
- Transformer with Untied Positional Encoding (TUPE). Code of paper "Rethinking Positional Encoding in Language Pre-training". Improve exis…☆251Updated 3 years ago