ocampor

scikit-learn

scikit-learn: machine learning in Python

pandas

Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more

bert

TensorFlow code and pre-trained models for BERT

numpy

The fundamental package for scientific computing with Python.

tuning_playbook

A playbook for systematically maximizing the performance of deep learning models.

celery

Distributed Task Queue (development branch)

matplotlib

matplotlib: plotting with Python

char-rnn

Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch

react-static

⚛️ 🚀 A progressive static site generator for React.

sentencepiece

Unsupervised text tokenizer for Neural Network-based text generation.

trax

Trax — Deep Learning with Clear Code and Speed

scikit-image

Image processing in Python

xmltodict

Python module that makes working with XML feel like you are working with JSON

fastpages

An easy to use blogging platform, with enhanced support for Jupyter Notebooks.

torch-rnn

Efficient, reusable RNNs and LSTMs for torch

swift-numerics

Advanced mathematical types and functions for Swift

language

Shared repository for open-sourced projects from the Google AI Language team.

deep-siamese-text-similarity

Tensorflow based implementation of deep siamese LSTM network to capture phrase/sentence similarity using character/word embeddings

cs224n-Squad-Project

nbval

A py.test plugin to validate Jupyter notebooks

Condenser

EMNLP 2021 - Pre-training architectures for dense retrieval

ganbert

Enhancing the BERT training with Semi-supervised Generative Adversarial Networks

Reranker

Build Text Rerankers with Deep Language Models

py_entitymatching

chars2vec

Character-based word embeddings model based on RNN for handling real world texts

py_stringmatching

A comprehensive and scalable set of string tokenizers and similarity measures in Python

dataset-person-name-disambiguation

creating a dataset for person name disambiguation using combination of sources like wikipedia, DBLP authors and PPDB.

mores_plus

MORES

name_pairs