jm-kang

llama

Inference code for LLaMA models

bert

TensorFlow code and pre-trained models for BERT

alpaca-lora

Instruct-tune LLaMA on consumer hardware

qlora

QLoRA: Efficient Finetuning of Quantized LLMs

DeepLearningZeroToAll

TensorFlow Basic Tutorial Labs

nlpaug

Data augmentation for NLP

siamese-triplet

Siamese and triplet networks with online pair/triplet mining in PyTorch

anserini

Anserini is a Lucene toolkit for reproducible information retrieval research

Parrot_Paraphraser

A practical and feature-rich paraphrasing framework to augment human intents in text form to build robust NLU models for conversational engines. Created by Prithiviraj Damodaran. Open to pull requests and other forms of collaboration.

acl2020-openqa-tutorial

ACL2020 Tutorial: Open-Domain Question Answering

torchgpipe

A GPipe implementation in PyTorch

biomedical

Tools for curating biomedical training data for large-scale language modeling

learning_to_retrieve_reasoning_paths

The official implementation of ICLR 2020, "Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering".

MRQA-Shared-Task-2019

Resources for the MRQA 2019 Shared Task

UnsupervisedQA

Unsupervised Question answering via Cloze Translation

www_personal

Personal Webpage

neural-question-generation

Pytorch implementation of Paragraph-level Neural Question Generation with Maxout Pointer and Gated Self-attention Networks

question-generation

Neural Models for Key Phrase Detection and Question Generation

Moducon-Docker-tf-setup

모두의연구소 2018 모두콘 '도커로 딥러닝 개발환경 올리기' 발표자료

cs500

Moved to https://cp-git.kaist.ac.kr/jeehoon.kang/cs500

HiNT

Implementation of Hierarchical Neural maTching model proposed in SIGIR'18 for ad-hoc retrieval

schema-to-json

Schema-Driven Information Extraction from Heterogeneous Tables

SafeAI

Reusable, Easy-to-use Uncertainty module package built with Tensorflow, Keras

Wikidata_relation_extractor

Code to extract KB triples from given contexts using Wikidata API

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.

Distill-or-Annotate

ACL 2023. Distill or Annotate? Cost-Efficient Fine-Tuning of Compact Models

feed100-client

feed100-server

feed100-web

ionic-sample

sample test