deep-spin / entmaxLinks
The entmax mapping and its loss, a family of sparse softmax alternatives.
☆447Updated last year
Alternatives and similar repositories for entmax
Users that are interested in entmax are comparing it to the libraries listed below
Sorting:
- Implementation of Sparsemax activation in Pytorch☆163Updated 5 years ago
- Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention☆269Updated 4 years ago
- The Noise Contrastive Estimation for softmax output written in Pytorch☆319Updated 5 years ago
- Transformer with Untied Positional Encoding (TUPE). Code of paper "Rethinking Positional Encoding in Language Pre-training". Improve exis…☆252Updated 3 years ago
- Understanding the Difficulty of Training Transformers☆330Updated 3 years ago
- Fully featured implementation of Routing Transformer☆298Updated 3 years ago
- ☆315Updated 3 years ago
- Implementation of https://arxiv.org/abs/1904.00962☆376Updated 4 years ago
- My take on a practical implementation of Linformer for Pytorch.☆420Updated 3 years ago
- PyTorch implementation of "Lagging Inference Networks and Posterior Collapse in Variational Autoencoders" (ICLR 2019)☆185Updated 4 years ago
- ☆219Updated 5 years ago
- ☆196Updated 2 years ago
- ☆212Updated last year
- Implementation of the "Poincare Glove: Hyperbolic word embeddings" paper☆88Updated 4 years ago
- Source code for the paper "Hyperbolic Neural Networks", https://arxiv.org/abs/1805.09112☆179Updated 4 years ago
- Implementation of Universal Transformer in Pytorch☆263Updated 6 years ago
- Long Range Arena for Benchmarking Efficient Transformers☆764Updated last year
- Fast, general, and tested differentiable structured prediction in PyTorch☆1,115Updated 3 years ago
- Code for Multi-Head Attention: Collaborate Instead of Concatenate☆151Updated 2 years ago
- Optimus: the first large-scale pre-trained VAE language model☆391Updated 2 years ago
- Transformer training code for sequential tasks☆611Updated 4 years ago
- This is a repository with the code for the ACL 2019 paper "Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, t…☆313Updated 4 years ago
- Generative Flow based Sequence-to-Sequence Toolkit written in Python.☆246Updated 5 years ago
- Code for EMNLP18 paper "Spherical Latent Spaces for Stable Variational Autoencoders"☆170Updated 6 years ago
- Pretrain and finetune ELECTRA with fastai and huggingface. (Results of the paper replicated !)☆330Updated last year
- Open source code for paper "Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere" ICML 2…☆454Updated 3 years ago
- Implementation of gMLP, an all-MLP replacement for Transformers, in Pytorch☆430Updated 4 years ago
- LAnguage Modelling Benchmarks☆138Updated 5 years ago
- An LSTM in PyTorch with best practices (weight dropout, forget bias, etc.) built-in. Fully compatible with PyTorch LSTM.☆134Updated 5 years ago
- A simple and working implementation of Electra, the fastest way to pretrain language models from scratch, in Pytorch☆231Updated 2 years ago