guolinke

TUPE

Transformer with Untied Positional Encoding (TUPE). Code of paper "Rethinking Positional Encoding in Language Pre-training". Improve existing models like BERT.

boosting_tree_benchmarks

deep-learning-benchmarks

fused_ops

lightgbm-ci-docker

This is the docker for LightGBM CI

pytorch-docker

sentencepiece

Unsupervised text tokenizer for Neural Network-based text generation.

apex

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

arxiv-sanity-preserver

Web interface for browsing, search and filtering recent arxiv submissions

azhpc-images

Scripts for installing HPC libraries, tools, to be used in Azure HPC images

BetterChatGPT

An amazing UI for OpenAI's ChatGPT (Website + Windows + MacOS + Linux)

category_encoders

A library of sklearn compatible categorical variable encoders

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

guolinke

machinelearning

ML.NET is an open source and cross-platform machine learning framework for .NET.

nccl

Optimized primitives for collective multi-GPU communication

openfold

Trainable PyTorch reproduction of AlphaFold 2

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

rdkit

The official sources for the RDKit library

recommenders

Best Practices on Recommendation Systems

sparsity

R package for loading/saving sparse matrices (dgCMatrix) to SVMlight (LibFM, xgboost, LightGBM, H2O, etc.)

tokenizers

💥Fast State-of-the-Art Tokenizers optimized for Research and Production

transformers

🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.

github_metrics

guolinke.github.io