nzhiltsov's Stars
google-research/bert
TensorFlow code and pre-trained models for BERT
facebook/rocksdb
A library that provides an embeddable, persistent key-value store for fast storage.
fastai/fastai
The fastai deep learning library
openai/gpt-2
Code for the paper "Language Models are Unsupervised Multitask Learners"
apache/mxnet
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more
oracle/graal
GraalVM compiles Java applications into native executables that start instantly, scale fast, and use fewer compute resources 🚀
flairNLP/flair
A very simple framework for state-of-the-art Natural Language Processing (NLP)
spotify/annoy
Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk
allenai/allennlp
An open-source NLP research library, built on PyTorch.
google/dopamine
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
google/sentencepiece
Unsupervised text tokenizer for Neural Network-based text generation.
VowpalWabbit/vowpal_wabbit
Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.
hyperopt/hyperopt
Distributed Asynchronous Hyperparameter Optimization in Python
facebookresearch/nevergrad
A Python toolbox for performing gradient-free optimization
kimiyoung/transformer-xl
facebookresearch/LASER
Language-Agnostic SEntence Representations
facebookresearch/PyTorch-BigGraph
Generate embeddings from large-scale graph-structured data.
facebookresearch/MUSE
A library for Multilingual Unsupervised or Supervised word Embeddings
google-deepmind/trfl
TensorFlow Reinforcement Learning
Tinche/aiofiles
File support for asyncio
tensorflow/ranking
Learning to Rank in TensorFlow
salesforce/awd-lstm-lm
LSTM and QRNN Language Model Toolkit for PyTorch
allenai/bilm-tf
Tensorflow implementation of contextualized word representations from bi-directional language models
marcotcr/anchor
Code for "High-Precision Model-Agnostic Explanations" paper
pixelogik/NearPy
Python framework for fast (approximated) nearest neighbour search in large, high-dimensional data sets using different locality-sensitive hashes.
byronknoll/cmix
cmix is a lossless data compression program aimed at optimizing compression ratio at the cost of high CPU/memory usage.
tolstikhin/wae
Wasserstein Auto-Encoders
ssemeniuta/textvae
Theano code for experiments in the paper "A Hybrid Convolutional Variational Autoencoder for Text Generation."
google/TrustScore
To Trust Or Not To Trust A Classifier. A measure of uncertainty for any trained (possibly black-box) classifier which is more effective than the classifier's own implied confidence (e.g. softmax probability for a neural network).
codeforamerica/naics-api
Basic API to return NAICS codes and information