anttttti

Wordbatch

Python library for distributed AI processing pipelines, using swappable scheduler backends.

kaggle-outbrain-click-prediction

pyxDamerauLevenshtein

pyxDamerauLevenshtein implements the Damerau-Levenshtein (DL) edit distance algorithm for Python in Cython for high performance.

babelcode

boosted-embeddings

Source code for the article.

DeBERTa

The implementation of DeBERTa

dlrm

An implementation of a deep learning recommendation model (DLRM)

flockserve

Open-source Sky Computing Inference Endpoint

HGAT

Heterogeneous graph attention network for semi-supervised short text classification (EMNLP 2019, TOIS 2021)

HyperGAT_TextClassification

Implementation of EMNLP2020 -- Be More with Less: Hypergraph Attention Networks for Inductive Text Classification

mercari-solution

Mercari 1st place solution (kaggle)

ng-numpy-randomstate

Numpy-compatible random number generator that supports multiple core psuedo RNGs and explicitly parallel generation.

py-lz4framed

LZ4-frame library for Python (via C bindings)

randomgen

Numpy-compatible bit generators and add some random variate distributions missing from NumPy.

ray

An open source framework that provides a simple, universal API for building distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.

rossum

Python API Client & a command line interface for controlling Rossum

SHINE-EMNLP21

Codes for SHINE published in EMNLP 2021.

text-clf-baselines

Collection of simple yet strong baselines for text classification.

text-generation-inference

Text-Level-GNN

Text Level Graph Neural Network for Text Classification

xgboost

Large-scale and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, on single node, hadoop yarn and more.