kyoungrok0517

Wikidata_relation_extractor

Code to extract KB triples from given contexts using Wikidata API

ARENA_3.0

art

Code and models for the paper "Questions Are All You Need to Train a Dense Passage Retriever (TACL 2023)"

bashidioms-examples

Example code from O'Reilly's bash Idioms

BERT-QPP

BERT-QPP: Contextualized Pre-trained transformers for Query Performance Prediction

BERTopic

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

big-ann-benchmarks

Framework for evaluating ANNS algorithms on billion scale datasets.

charset_normalizer

Truly universal encoding detector in pure Python

CircuitsVis

Mechanistic Interpretability Visualizations using React

dictionary_learning

dropout

Code release for "Dropout Reduces Underfitting"

einops

Deep learning operations reinvented (for pytorch, tensorflow, jax and others)

gpt3-blog-title-optimizer

Python code for building a GPT-3 based technical blog post optimizer.

imagen-pytorch

Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch

ingredients

lightning-transformers

Flexible interface for high-performance research using SOTA Transformers leveraging Pytorch Lightning, Transformers, and Hydra.

nanoColBERT

Simple replication of [ColBERT-v1](https://arxiv.org/abs/2004.12832).

natural-questions

Natural Questions (NQ) contains real user questions issued to Google search, and answers found from Wikipedia by annotators. NQ is designed for the training and evaluation of automatic question answering systems.

NC-BERT

BERT capable of numerical extrapolation over text (solving arithmetic problems over textual reasoning dataset)

pmi-masking

This repository includes the masking vocabulary used in the ICLR 2021 spotlight PMI-Masking paper

SAELens

Training Sparse Autoencoders on Language Models

semantic-python-overview

(subjective) overview of projects which are related both to python and semantic technologies (RDF, OWL, Reasoning, ...)

skku_tutorial_2

skku_tutorial_3

splade

SPLADE: sparse neural search (SIGIR21, SIGIR22)

stat_rethinking_2024

Streamlit-Authenticator

A secure authentication module to validate user credentials in a Streamlit application.

Style-Transformer-for-MSD

Expert-laymen style transfer model based on the Style Transformer (Dai. et al., 2019). This code is based on the MSD dataset (Cao et al., 2020), which is a task for style transfer between an expert-level language to a laymen language for the ease of communication.

subspace-clustering

Toolbox for large scale subspace clustering

the-art-of-command-line

Master the command line, in one page