greentfrapp / attention-primerLinks
A demonstration of the attention mechanism with some toy experiments and explanations.
☆108Updated 7 years ago
Alternatives and similar repositories for attention-primer
Users that are interested in attention-primer are comparing it to the libraries listed below
Sorting:
- Configure Python functions explicitly and safely☆126Updated 9 months ago
- Training Transformer-XL on 128 GPUs☆140Updated 5 years ago
- ☆28Updated 6 years ago
- Code for Neural Arithmetic Units (ICLR) and Measuring Arithmetic Extrapolation Performance (SEDL|NeurIPS)☆146Updated 4 years ago
- ☆153Updated 5 years ago
- Probabilistic classification in PyTorch/TensorFlow/scikit-learn with Fenchel-Young losses☆188Updated last year
- Pip-installable differentiable stacks in PyTorch!☆65Updated 4 years ago
- learning to search in pytorch☆110Updated 5 years ago
- Experiment orchestration☆102Updated 5 years ago
- Python implementation of GLN in different frameworks☆97Updated 4 years ago
- The Annotated Encoder Decoder with Attention☆166Updated 4 years ago
- ☆64Updated 5 years ago
- Visualising the Transformer encoder☆111Updated 4 years ago
- AI/ML citation graph with postgres + graphql☆188Updated 5 years ago
- ☆103Updated 4 years ago
- Mixture Density Networks (Bishop, 1994) tutorial in JAX☆60Updated 5 years ago
- Blazingly fast capsule networks in 75 lines of pytorch+einops☆26Updated 3 years ago
- ☆75Updated 5 years ago
- Pytorch Cheatsheet☆90Updated 7 years ago
- TBA☆76Updated 6 years ago
- ☆45Updated 5 years ago
- Synthetic book pages created with a PGGAN☆73Updated 6 years ago
- Visualizing memorization in RNNs☆66Updated 4 years ago
- ☆88Updated 7 years ago
- PyTorch functions and utilities to make your life easier☆194Updated 4 years ago
- Weekly humanitarian AI reading group at Mila.☆21Updated 6 years ago
- Provides a systematic and extensible way to build, train, evaluate, and tune deep learning models using PyTorch.☆94Updated last year
- The code repository for examples in the O'Reilly book 'Generative Deep Learning' using Pytorch☆184Updated 5 years ago
- Torchélie is a set of utility functions, layers, losses, models, trainers and other things for PyTorch.☆110Updated last week
- PyTorch implementation of the NIPS'17 paper Training Deep Networks without Learning Rates Through Coin Betting.