jun-seok-lee Goto Github PK

followers: 1.0 following: 12.0 repos: 32.0 gists: 1.0

Name: Junseok Lee

Type: User

Location: Seoul, South Korea

Motivation for studying AI

I am an undergraduate who dreams of contributing to the open-source community.

During my time at the NANUS startup, I developed an interest in AI including NLP.

However, I encounterd numerous challenges in developing an application from scratch, even a demo version.

This experience led me to wish for guidance from an assistant.

Research Interests

I'm interested in multimodal downstream tasks towards AGI which is more human-like than AI.

Nowadays, I'm developing interests especially in 1) Multimodal Chain-of-Thought, 2) Video Question Answering, 3) Visual Programming.

Ultimately, I wish the marginalized continues to learn what they want via multimodal LLM without any difficulties.

Furthermore, I aim to combine personalized learning with cooperative study.

Languages & & Skills:

Database:

Programming Languages:

However, I'm more familiar with python or pytorch than C or Java.

Others:

IDEs and Tools:

Junseok Lee's Projects

ai-for-beginners

12 Weeks, 24 Lessons, AI for All!

blog-finetuning-llama-adapters

Supplementary material for "Understanding Parameter-Efficient Finetuning of Large Language Models: From Prefix Tuning to Adapters"

clip

This repository is about finetuning CLIP and zero-shot classification

decision-transformer

Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.

deep-rl-class

This repo contains the syllabus of the Hugging Face Deep Reinforcement Learning Course.

deeprl-tutorials

Contains high quality implementations of Deep Reinforcement Learning algorithms written in PyTorch

firenzedt

Crawling media website, the table of Florence(피렌체의 식탁)

gdrl

Grokking Deep Reinforcement Learning

generative-ai-for-beginners

12 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/

generative-ai-with-llms

In Generative AI with Large Language Models (LLMs), you’ll learn the fundamentals of how generative AI works, and how to deploy it in real-world applications.

human-eval

Create problem json file based on the format of HumanEval.jsonl developed by OpenAI

jun-seok-lee

korbertsum

KorBertSum을 구현하기 위한 tokenization부터 embedding까지의 전처리

kpfbertsum

langchain-kr

LangChain 공식 Document, Cookbook, 그 밖의 실용 예제를 바탕으로 작성한 한국어 튜토리얼입니다. 본 튜토리얼을 통해 LangChain을 더 쉽고 효과적으로 사용하는 방법을 배울 수 있습니다.

lilalio

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

llm_recipes

A set of scripts and notebooks on LLM finetunning and dataset creation

machine-learning

머신러닝 입문자 혹은 스터디를 준비하시는 분들에게 도움이 되고자 만든 repository입니다. (This repository is intented for helping whom are interested in machine learning study)

machine-translation

kiwi tokenizer를 활용한 영한 기계번역(NOT WORKING)

materials-for-learning

이 레포지토리는 공부하면서 도움이 되었던 자료(강의/블로그/책) 등을 모아 놓은 공간입니다.(영어와 한국어가 섞여있는 점 유의하며 보시길 바랍니다)

ml-engineering

Machine Learning Engineering Online Book

mml

Mathematics For Machine Learning Study

open-review-analysis

pytorch-lightning

Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.

react-native

A framework for building native applications using React

rt-2

Democratization of RT-2 "RT-2: New model translates vision and language into action"

tinygpt-v

TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones

transformers-tutorials

This repository contains demos I made with the Transformers library by HuggingFace.

viper

Code for the paper "ViperGPT: Visual Inference via Python Execution for Reasoning"