yuhongqian

reverse-interview

Questions to ask the company during your interview

sentence-transformers

Multilingual Sentence & Image Embeddings with BERT

DeepLearningExamples

State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.

stanza

Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages

apprtc

appr.tc has been shutdown. Please use the Dockerfile to run your own test/dev instance.

SimCSE

[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821

fast-transformers

Pytorch library for fast transformer implementations

webRTC.io

An abstraction layer for webRTC. Aim is to simplify the HTML5 web standard webRTC in a similar manner to socket.io w/ websockets. Highly experimental technology

awesome-self-supervised-gnn

Papers about pretraining and self-supervised learning on Graph Neural Networks (GNN).

beir

A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.

sparse_attention

Examples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers"

opencv-processing

OpenCV for Processing. A creative coding computer vision library based on the official OpenCV Java API

DiskANN

Graph-structured Indices for Scalable, Fast, Fresh and Filtered Approximate Nearest Neighbor Search

DataAug4NLP

Collection of papers and resources for data augmentation for NLP.

pytorch_block_sparse

Fast Block Sparse Matrices for Pytorch

Text-Attention-Heatmap-Visualization

Plot the vector graph of attention based text visualisation

MuTual

A Dataset for Multi-Turn Dialogue Reasoning

pytrec_eval

pytrec_eval is an Information Retrieval evaluation tool for Python, based on the popular trec_eval.

sputnik

A library of GPU kernels for sparse matrix operations.

multihop_dense_retrieval

Multi-hop dense retrieval for question answering

numnet_plus

This is the official code repository for NumNet+(https://leaderboard.allenai.org/drop/submission/blu418v76glsbnh1qvd0)

torch-blocksparse

Block-sparse primitives for PyTorch

Annotated-WikiExtractor

Simple Wikipedia plain text extractor with article link annotations and Hadoop support.

rotten-tomatoes-dataset

Scraping Rotten Tomatoes then Sentiment Analysis with Logit Written Manually

merge-spmm

Code for paper "Design Principles for Sparse Matrix Multiplication on the GPU" accepted to Euro-Par 2018

cutlass_tilesparse

CUDA templates for tile-sparse matrix multiplication based on CUTLASS.

meet-api

this is an unofficial google meet-api that takes oath2 credentials as input and according to your time and date (that is provided by the user) gives you the meeting links.

DL-Hard

Deep Learning Hard (DL-HARD) is a new annotated dataset extending TREC Deep Learning benchmark.

NumNet

Anchors

Source code of CIKM2021 Paper 'Pre-training for Ad-hoc Retrieval: Hyperlink is Also You Need'