guolinke / TUPELinks
Transformer with Untied Positional Encoding (TUPE). Code of paper "Rethinking Positional Encoding in Language Pre-training". Improve existing models like BERT.
☆251Updated 3 years ago
Alternatives and similar repositories for TUPE
Users that are interested in TUPE are comparing it to the libraries listed below
Sorting:
- 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…☆244Updated 3 years ago
- ☆218Updated 5 years ago
- For the code release of our arXiv paper "Revisiting Few-sample BERT Fine-tuning" (https://arxiv.org/abs/2006.05987).☆184Updated 2 years ago
- Understanding the Difficulty of Training Transformers☆329Updated 3 years ago
- Source code of paper "BP-Transformer: Modelling Long-Range Context via Binary Partitioning"☆128Updated 4 years ago
- Generative Flow based Sequence-to-Sequence Toolkit written in Python.☆245Updated 5 years ago
- ⛵️The official PyTorch implementation for "BERT-of-Theseus: Compressing BERT by Progressive Module Replacing" (EMNLP 2020).☆313Updated 2 years ago
- Code for the RecAdam paper: Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting.☆117Updated 4 years ago
- Pytorch Implementation of ALBERT(A Lite BERT for Self-supervised Learning of Language Representations)☆226Updated 4 years ago
- Codes for "Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View"☆148Updated 6 years ago
- Implementation of the paper Tree Transformer☆214Updated 5 years ago
- ☆252Updated 2 years ago
- PyTorch Implementation of "Non-Autoregressive Neural Machine Translation"☆269Updated 3 years ago
- ☆83Updated 5 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 4 years ago
- ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators☆91Updated 3 years ago
- The entmax mapping and its loss, a family of sparse softmax alternatives.☆439Updated last year
- Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention☆264Updated 3 years ago
- Neural Text Generation with Unlikelihood Training☆309Updated 3 years ago
- Code for the paper "Are Sixteen Heads Really Better than One?"☆172Updated 5 years ago
- Implementation of Universal Transformer in Pytorch☆260Updated 6 years ago
- pytorch; mask language model ; bert☆72Updated 5 years ago
- Tracking the progress in non-autoregressive generation (translation, transcription, etc.)☆306Updated 2 years ago
- PyTorch implementation of beam search decoding for seq2seq models☆337Updated 2 years ago
- [NeurIPS 2021] COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining☆117Updated last year
- Optimus: the first large-scale pre-trained VAE language model☆387Updated last year
- Transformers without Tears: Improving the Normalization of Self-Attention☆131Updated last year
- ☆96Updated 4 years ago
- Code for Multi-Head Attention: Collaborate Instead of Concatenate☆152Updated 2 years ago
- FairSeq repo with Apollo optimizer☆114Updated last year