deep-spin / entmax
The entmax mapping and its loss, a family of sparse softmax alternatives.
☆406Updated 2 months ago
Related projects: ⓘ
- Transformer with Untied Positional Encoding (TUPE). Code of paper "Rethinking Positional Encoding in Language Pre-training". Improve exis…☆249Updated 2 years ago
- Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention☆252Updated 3 years ago
- The Noise Contrastive Estimation for softmax output written in Pytorch☆318Updated 4 years ago
- Implementation of Sparsemax activation in Pytorch☆155Updated 4 years ago
- Understanding the Difficulty of Training Transformers☆325Updated 2 years ago
- Code for Multi-Head Attention: Collaborate Instead of Concatenate☆148Updated last year
- Fast, general, and tested differentiable structured prediction in PyTorch☆1,105Updated 2 years ago
- ☆308Updated 2 years ago
- Fully featured implementation of Routing Transformer☆282Updated 2 years ago
- My take on a practical implementation of Linformer for Pytorch.☆403Updated 2 years ago
- Implementation of https://arxiv.org/abs/1904.00962☆366Updated 3 years ago
- Transformer training code for sequential tasks☆608Updated 3 years ago
- ☆211Updated 4 years ago
- ☆204Updated 5 months ago
- LAnguage Modelling Benchmarks☆138Updated 4 years ago
- Implementation of Universal Transformer in Pytorch☆256Updated 5 years ago
- PyTorch implementation of "Lagging Inference Networks and Posterior Collapse in Variational Autoencoders" (ICLR 2019)☆183Updated 3 years ago
- Code for the paper "Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks"☆577Updated 5 years ago
- Minimal RNN classifier with self-attention in Pytorch☆148Updated 2 years ago
- Pretrain and finetune ELECTRA with fastai and huggingface. (Results of the paper replicated !)☆323Updated 8 months ago
- PyTorch implementation of Hash Embeddings (NIPS 2017). Submission to the NIPS Implementation Challenge.☆191Updated 5 years ago
- Source code for the paper "Hyperbolic Neural Networks", https://arxiv.org/abs/1805.09112☆171Updated 3 years ago
- Generative Flow based Sequence-to-Sequence Toolkit written in Python.☆243Updated 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…☆296Updated 3 years ago
- Long Range Arena for Benchmarking Efficient Transformers☆711Updated 9 months ago
- Official PyTorch Repo for "ReZero is All You Need: Fast Convergence at Large Depth"☆405Updated last month
- PyTorch Re-Implementation of "Generating Sentences from a Continuous Space" by Bowman et al 2015 https://arxiv.org/abs/1511.06349☆584Updated 3 weeks ago
- Optimus: the first large-scale pre-trained VAE language model☆367Updated last year
- Open source code for paper "Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere" ICML 2…☆429Updated 2 years ago
- Sparse and structured neural attention mechanisms☆224Updated 4 years ago