Stars
Minimalistic large language model 3D-parallelism training
Source code of our paper "Solving Constrained Variational Inequalities via a First-order Interior Point-based Method", ICLR 2023.
A set of Matlab functions for visualizing Bohemian eigenvalues.
higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.
Text Classification Algorithms: A Survey
Snorkel MeTaL: A framework for training models with multi-task weak supervision
Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
CoLa - Decentralized Linear Learning: https://arxiv.org/abs/1808.04883
Multi-class confusion matrix library in Python
An open-source NLP research library, built on PyTorch.
Easy to use OpenStreetMap editor for Android
General purpose unsupervised sentence representations
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Models and examples built with TensorFlow
The Museum of Modern Art (MoMA) collection data
A curated list of data science blogs
Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch
Master the command line, in one page
CockroachDB — the cloud native, distributed SQL database designed for high availability, effortless scale, and control over data placement.
CoreNLP: A Java suite of core NLP tools for tokenization, sentence segmentation, NER, parsing, coreference, sentiment analysis, etc.
A cool way to communicate with people around you. @facebookHackathon
Lightweight library to build and train neural networks in Theano