Soonhwan-Kwon

CLIP

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

jina

☁️ Build multimodal AI applications with cloud-native stack

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

open_clip

An open source implementation of CLIP.

FLAML

A fast library for AutoML and tuning. Join our Discord: https://discord.gg/Cppx2vSPVP.

vissl

VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.

GLIP

Grounded Language-Image Pre-training

P-tuning-v2

An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks

DeBERTa

The implementation of DeBERTa

pet

This repository contains the code for "Exploiting Cloze Questions for Few-Shot Text Classification and Natural Language Inference"

multimodal

TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.

mup

maximal update parametrization (µP)

question_generation

Neural question generation using transformers

deduplicate-text-datasets

wit

WIT (Wikipedia-based Image Text) Dataset is a large multimodal multilingual dataset comprising 37M+ image-text sets with 11M+ unique images across 100+ languages.

P-tuning

A novel method to tune language models. Codes and datasets for paper ``GPT understands, too''.

python-paillier

A library for Partially Homomorphic Encryption in Python

Question-Generation-Paper-List

A summary of must-read papers for Neural Question Generation (NQG)

clip_playground

An ever-growing playground of notebooks showcasing CLIP's impressive zero-shot capabilities

L-Verse

L-Verse: Bidirectional Generation Between Image and Text

ICLR2022-OpenReviewData

Crawl & visualize ICLR papers and reviews.

mutransformers

some common Huggingface transformers in maximal update parametrization (µP)

Learning-in-the-Frequency-Domain

biokg

A Knowledge Graph for Relational Learning On Biological Data

hypermix

Code for text augmentation method leveraging large-scale language models

minimal-rnr-qa

[NAACL 2021] Designing a Minimal Retrieve-and-Read System for Open-Domain Question Answering

Dacon

Dacon에서 진행하는 경진대회의 코드를 올려둔 공간입니다.

Homomorphic-Encryption

refuel-open-domain-qa

CAQA

[EMNLP 2021] PyTorch Implementation of Contrastive Domain Adaptation for Question Answering using Limited Text Corpora