google-deepmind / lamb
LAnguage Modelling Benchmarks
☆138Updated 4 years ago
Related projects: ⓘ
- An LSTM in PyTorch with best practices (weight dropout, forget bias, etc.) built-in. Fully compatible with PyTorch LSTM.☆133Updated 4 years ago
- ☆211Updated 4 years ago
- Pytorch implementation of R-Transformer. Some parts of the code are adapted from the implementation of TCN and Transformer.☆224Updated 5 years ago
- A simple module consistently outperforms self-attention and Transformer model on main NMT datasets with SoTA performance.☆86Updated last year
- Latent Alignment and Variational Attention☆326Updated 5 years ago
- Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning☆311Updated 4 years ago
- Code for Multi-Head Attention: Collaborate Instead of Concatenate☆148Updated last year
- Implementation of the "Poincare Glove: Hyperbolic word embeddings" paper☆84Updated 3 years ago
- Sequence to Sequence Models in PyTorch☆44Updated last month
- PyTorch implementations of LSTM Variants (Dropout + Layer Norm)☆136Updated 3 years ago
- Code for EMNLP 2019 paper "Attention is not not Explanation"☆57Updated 3 years ago
- Implementation of Universal Transformer in Pytorch☆256Updated 5 years ago
- Source code for the paper "Hyperbolic Neural Networks", https://arxiv.org/abs/1805.09112☆171Updated 3 years ago
- Efficient Transformers for research, PyTorch and Tensorflow using Locality Sensitive Hashing☆93Updated 4 years ago
- PyTorch implementation of "Lagging Inference Networks and Posterior Collapse in Variational Autoencoders" (ICLR 2019)☆183Updated 3 years ago
- Minimal RNN classifier with self-attention in Pytorch☆148Updated 2 years ago
- ☆308Updated 2 years ago
- The entmax mapping and its loss, a family of sparse softmax alternatives.☆406Updated 2 months ago
- Checking the interpretability of attention on text classification models☆47Updated 5 years ago
- ☆155Updated 6 years ago
- ☆83Updated 4 years ago
- Code for EMNLP18 paper "Spherical Latent Spaces for Stable Variational Autoencoders"☆165Updated 5 years ago
- Bayesian Deep Active Learning for Natural Language Processing Tasks☆147Updated 5 years ago
- A smoother activation function (undergrad code)☆104Updated 4 years ago
- Bi-Directional Block Self-Attention☆124Updated 6 years ago
- PyTorch DataLoader for seq2seq☆83Updated 5 years ago
- A quick walk-through of the innards of LSTMs and a naive implementation of the Mogrifier LSTM paper in PyTorch☆73Updated 4 years ago
- NeurIPS 2019 - Learning Data Manipulation for Augmentation and Weighting☆107Updated 4 years ago
- Code for NIPS 2018 paper 'Frequency-Agnostic Word Representation'☆118Updated 5 years ago
- Cascaded Text Generation with Markov Transformers☆126Updated last year