guolinke / TUPE
Transformer with Untied Positional Encoding (TUPE). Code of paper "Rethinking Positional Encoding in Language Pre-training". Improve existing models like BERT.
☆250Updated 3 years ago
Alternatives and similar repositories for TUPE:
Users that are interested in TUPE are comparing it to the libraries listed below
- For the code release of our arXiv paper "Revisiting Few-sample BERT Fine-tuning" (https://arxiv.org/abs/2006.05987).☆184Updated last year
- Source code of paper "BP-Transformer: Modelling Long-Range Context via Binary Partitioning"☆127Updated 3 years ago
- Understanding the Difficulty of Training Transformers☆328Updated 2 years ago
- ☆83Updated 5 years ago
- ⛵️The official PyTorch implementation for "BERT-of-Theseus: Compressing BERT by Progressive Module Replacing" (EMNLP 2020).☆309Updated last year
- ☆251Updated 2 years ago
- A masked language modeling objective to train a model to predict any subset of the target words, conditioned on both the input text and a…☆242Updated 3 years ago
- ☆215Updated 4 years ago
- Generative Flow based Sequence-to-Sequence Toolkit written in Python.☆244Updated 5 years ago
- ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators☆91Updated 3 years ago
- Code for the RecAdam paper: Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting.☆115Updated 4 years ago
- Code for the ICML'20 paper "Improving Transformer Optimization Through Better Initialization"☆89Updated 4 years ago
- Implementation of the paper Tree Transformer☆213Updated 4 years ago
- Codes for "Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View"☆148Updated 5 years ago
- ☆97Updated 4 years ago
- Pytorch Implementation of ALBERT(A Lite BERT for Self-supervised Learning of Language Representations)☆226Updated 3 years ago
- An implementation of masked language modeling for Pytorch, made as concise and simple as possible☆179Updated last year
- The entmax mapping and its loss, a family of sparse softmax alternatives.☆426Updated 8 months ago
- [ICML 2021 Oral] We show pure attention suffers rank collapse, and how different mechanisms combat it.☆164Updated 4 years ago
- Worth-reading papers and related resources on attention mechanism, Transformer and pretrained language model (PLM) such as BERT. 值得一读的注意力…☆133Updated 3 years ago
- [NeurIPS 2021] COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining☆118Updated last year
- Code for the paper "Are Sixteen Heads Really Better than One?"☆171Updated 4 years ago
- PyTorch implementation of beam search decoding for seq2seq models☆337Updated 2 years ago
- My take on a practical implementation of Linformer for Pytorch.☆412Updated 2 years ago
- PyTorch Implementation of "Non-Autoregressive Neural Machine Translation"☆268Updated 3 years ago
- Tracking the progress in non-autoregressive generation (translation, transcription, etc.)☆307Updated last year
- Neural Text Generation with Unlikelihood Training☆309Updated 3 years ago
- This is the official code repository for NumNet+(https://leaderboard.allenai.org/drop/submission/blu418v76glsbnh1qvd0)☆177Updated 7 months ago
- Adversarial Training for Natural Language Understanding☆252Updated last year
- ☆176Updated 3 years ago