wangcho2k
Ph. D. in ECE / Research Engineer in Hyperscale AI, Foundation Model, NLP
42dot (@42dot, @hkmc-airlab)Pangyo, Gyeonggi, Republic of Korea
Pinned Repositories
42dot_LLM
42dot LLM consists of a pre-trained language model, 42dot LLM-PLM, and a fine-tuned model, 42dot LLM-SFT, which is trained to respond to user prompts and supports both languages simultaneously by training a large amount of Korean and English text.
alexa-with-dstc9-track1-dataset
DSTC9 Track 1 - Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access
bert
TensorFlow code and pre-trained models for BERT
charNgram2vec
Pre-training character n-gram embeddings
cnn-text-classification-tf
Convolutional Neural Network for Text Classification in Tensorflow
comparative-abusive-lang
Comparative Studies of Detecting Abusive Language on Twitter
confidence_intervals
Bootstrap resampling for some tasks
ContraPro
Contrastive evaluation of pronoun translation in neural machine translation
Cpp-Primer-Plus
C++ Primer Plus 6th Answers
Cpp-Tutorial-Samples
C++ tutorial code samples for those who want to start learning the language
wangcho2k's Repositories
wangcho2k/alexa-with-dstc9-track1-dataset
DSTC9 Track 1 - Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access
wangcho2k/bert
TensorFlow code and pre-trained models for BERT
wangcho2k/comparative-abusive-lang
Comparative Studies of Detecting Abusive Language on Twitter
wangcho2k/confidence_intervals
Bootstrap resampling for some tasks
wangcho2k/ContraPro
Contrastive evaluation of pronoun translation in neural machine translation
wangcho2k/Cpp-Tutorial-Samples
C++ tutorial code samples for those who want to start learning the language
wangcho2k/CycleGAN-tensorflow
Tensorflow implementation for learning an image-to-image translation without input-output pairs. https://arxiv.org/pdf/1703.10593.pdf
wangcho2k/dac_control
Arduino source code for controlling ComTrue Inc. CT7302 Audio SRC Bridge
wangcho2k/decaNLP
The Natural Language Decathlon: A Multitask Challenge for NLP
wangcho2k/DeepSpeedExamples
Example models using DeepSpeed
wangcho2k/dps
Data processing system for polyglot
wangcho2k/epg2xml
EPG 정보를 XML로 만드는 프로그램
wangcho2k/epg2xml_orig
XML 규격의 EPG를 만드는 파이썬 프로그램
wangcho2k/evalplus
Rigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024
wangcho2k/fastcampus-springboot-introduction
패스트 캠퍼스 스프링 부트 입문
wangcho2k/GitHubGraduation-2022
Join the GitHub Graduation Yearbook and "walk the stage" on June 11.
wangcho2k/GPT-4-LLM
Instruction Tuning with GPT-4
wangcho2k/gt-nlp-class
Course materials for Georgia Tech CS 4650 and 7650, "Natural Language"
wangcho2k/MASS
MASS: Masked Sequence to Sequence Pre-training for Language Generation
wangcho2k/namu-wiki-extractor
A library to extract plaintexts from the JSON dump file of namu wiki
wangcho2k/NeMo
NeMo: a toolkit for conversational AI
wangcho2k/PGPortfolio
PGPortfolio: Policy Gradient Portfolio, the source code of "A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem"(https://arxiv.org/pdf/1706.10059.pdf).
wangcho2k/pml2-book
Probabilistic Machine Learning: Advanced Topics
wangcho2k/polyglot
Polyglot: Large Language Models of Well-balanced Competence in Multi-languages
wangcho2k/refresh_room
mobamas refresh_room
wangcho2k/SemEval2018-Task3
This is the Github repository for SemEval-2018 Task 3
wangcho2k/tensor2tensor
Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
wangcho2k/text-dedup
All-in-one text de-duplication
wangcho2k/text-to-text-transfer-transformer
Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"
wangcho2k/wangcho2k.github.io