(ACL-IJCNLP 2021) Convolutions and Self-Attention: Re-interpreting Relative Positions in Pre-trained Language Models.
☆21Jul 13, 2022Updated 3 years ago
Alternatives and similar repositories for BERT_Convolutions
Users that are interested in BERT_Convolutions are comparing it to the libraries listed below
Sorting:
- ☆16May 6, 2021Updated 4 years ago
- Implementation for NATv2.☆23Feb 20, 2021Updated 5 years ago
- Official repository for Fourier model that can generate periodic signals☆10Mar 10, 2022Updated 3 years ago
- ☆31Jun 29, 2022Updated 3 years ago
- Code for Depth-wise Separable Convolutions: Performance Investigations☆19Jan 28, 2020Updated 6 years ago
- A pytorch implementation of the ICCV2021 workshop paper SimDis: Simple Distillation Baselines for Improving Small Self-supervised Models☆14Jul 15, 2021Updated 4 years ago
- ACL 2021: HiTransformer☆13May 29, 2021Updated 4 years ago
- Implementation of semi-supervised learning using PyTorch Lightning☆14Jul 25, 2024Updated last year
- ☆13Nov 7, 2021Updated 4 years ago
- Bag of MLP☆20May 31, 2021Updated 4 years ago
- Python implementation for paper: Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examples☆11Jun 12, 2018Updated 7 years ago
- Successfully training approximations to full-rank matrices for efficiency in deep learning.☆17Jan 5, 2021Updated 5 years ago
- ICLR 2021, Fair Mixup: Fairness via Interpolation☆59Sep 6, 2021Updated 4 years ago
- Locally Enhanced Self-Attention: Rethinking Self-Attention as Local and Context Terms☆20Nov 29, 2021Updated 4 years ago
- Webpage☆16Feb 16, 2024Updated 2 years ago
- LV-BERT: Exploiting Layer Variety for BERT (Findings of ACL 2021)☆18May 10, 2023Updated 2 years ago
- The baseline model code for WMT 2021 Triangular MT☆13Apr 7, 2021Updated 4 years ago
- Code of the COLING22 paper "uChecker: Masked Pretrained Language Models as Unsupervised Chinese Spelling Checkers"☆19Aug 17, 2022Updated 3 years ago
- pytorch implementation of "Contrastive Multiview Coding", "Momentum Contrast for Unsupervised Visual Representation Learning", and "Unsup…☆18Mar 23, 2020Updated 5 years ago
- Code for our paper "Prune and Replace NAS"☆17Jun 26, 2019Updated 6 years ago
- Object-aware Contrastive Learning for Debiased Scene Representation (NeurIPS 2021)☆45Oct 25, 2021Updated 4 years ago
- ☆15Dec 10, 2021Updated 4 years ago
- Code associated with the paper **SkipBERT: Efficient Inference with Shallow Layer Skipping**, at ACL 2022☆16Jun 22, 2022Updated 3 years ago
- ☆74Dec 8, 2022Updated 3 years ago
- Implementation of a Quantized Transformer Model☆19Mar 20, 2019Updated 6 years ago
- Stochastic Optimization for Global Contrastive Learning without Large Mini-batches☆20Mar 31, 2023Updated 2 years ago
- Displaced Aggregation Units for Convolutional Networks from "Spatially-Adaptive Filter Units for Deep Neural Networks" paper☆21Jun 27, 2024Updated last year
- The project is about predicting sets (of classes) from images.☆23Aug 31, 2021Updated 4 years ago
- Code for ACL2022 publication Transkimmer: Transformer Learns to Layer-wise Skim☆22Aug 21, 2022Updated 3 years ago
- ☆20Sep 28, 2020Updated 5 years ago
- ☆24Nov 21, 2023Updated 2 years ago
- PyTorch implementation of the paper The Lottery Ticket Hypothesis for Object Recognition☆23Apr 22, 2021Updated 4 years ago
- ☆21Jul 1, 2021Updated 4 years ago
- [CVPR 2022] "The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy" by Tianlong C…☆25Mar 9, 2022Updated 3 years ago
- Code for our paper: "Regularity Normalization: Neuroscience-Inspired Unsupervised Attention across Neural Network Layers".☆20Dec 28, 2021Updated 4 years ago
- MLP-Like Vision Permutator for Visual Recognition (PyTorch)☆192Mar 31, 2022Updated 3 years ago
- Implementation of the paper "Fine-Tuning Transformers: Vocabulary Transfer" https://arxiv.org/pdf/2112.14569.pdf☆20Dec 28, 2021Updated 4 years ago
- ☆135Feb 10, 2023Updated 3 years ago
- Source code for NAACL 2021 paper "TR-BERT: Dynamic Token Reduction for Accelerating BERT Inference"☆48May 25, 2022Updated 3 years ago