hendrycks / GELUsLinks
A smoother activation function (undergrad code)
☆110Updated 4 years ago
Alternatives and similar repositories for GELUs
Users that are interested in GELUs are comparing it to the libraries listed below
Sorting:
- Sparse and structured neural attention mechanisms☆223Updated 4 years ago
- LAnguage Modelling Benchmarks☆137Updated 5 years ago
- PyTorch Examples repo for "ReZero is All You Need: Fast Convergence at Large Depth"☆62Updated 10 months ago
- An implementation of MixMatch with PyTorch☆36Updated 4 years ago
- Re-implementation of the Noise Contrastive Estimation algorithm for pyTorch, following "Noise-contrastive estimation: A new estimation pr…☆45Updated 5 years ago
- Implements pytorch code for the Accelerated SGD algorithm.☆215Updated 7 years ago
- Adaptive Softmax implementation for PyTorch☆80Updated 6 years ago
- NeurIPS 2019 - Learning Data Manipulation for Augmentation and Weighting☆109Updated 4 years ago
- Code for Multi-Head Attention: Collaborate Instead of Concatenate☆151Updated last year
- PyTorch implementation of the NIPS'17 paper Training Deep Networks without Learning Rates Through Coin Betting.☆37Updated 7 years ago
- Implementation of Sparsemax activation in Pytorch☆160Updated 5 years ago
- ☆61Updated 2 years ago
- PyTorch implementations of LSTM Variants (Dropout + Layer Norm)☆136Updated 4 years ago
- LAMB Optimizer for Large Batch Training (TensorFlow version)☆120Updated 5 years ago
- Decoupled Weight Decay Regularization (ICLR 2019)☆275Updated 6 years ago
- Implementation of "Learning with Random Learning Rates" in PyTorch.☆102Updated 5 years ago
- Bi-Directional Block Self-Attention☆122Updated 7 years ago
- Latent Alignment and Variational Attention☆327Updated 6 years ago
- Configure Python functions explicitly and safely☆126Updated 6 months ago
- pytorch implement of Lookahead Optimizer☆190Updated 2 years ago
- ☆63Updated 7 years ago
- Checking the interpretability of attention on text classification models☆48Updated 5 years ago
- ☆74Updated 8 years ago
- Machine-generated summaries and highlights of the every accepted paper at Thirty-second Conference on Neural Information Processing Syste…☆71Updated 6 years ago
- Compression of NMT transformer model with tensor methods☆48Updated 5 years ago
- Code for EMNLP 2019 paper "Attention is not not Explanation"☆58Updated 4 years ago
- Unsupervised Data Augmentation experiments in PyTorch☆59Updated 5 years ago
- Source code for "Efficient Training of BERT by Progressively Stacking"☆112Updated 5 years ago
- ☆218Updated 4 years ago
- Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention☆264Updated 3 years ago