Giter VIP home page Giter VIP logo

Hyeongmin Moon

Intro

I am a AI engineer mainly researching about computer vision. Recently researching Diffusion Models, Large Language Models and theirs Quantization methods too.

For me, Development does not happen just in computer. Development means All actions that present a solution when a problem is given, and if the real action is more appropriate than the code, I prefer to adopt it.

Recent interests

  • Train/Inference speed optimization for big-models(exllama, Stable Diffusion, vllm, etc)
  • Finetuning LLMs(full-finetuning, LoRA, QLoRA)
  • Large model Quantization into 4bit(GPTQ, AWQ)
  • Few-data learning using CrossValidation & Stacking Ensemble
  • MoE (Mixture of Experts)
  • More Interests sorted by category

Education & Skills

Skills_202403

Projects

Web CV last updated: 2023.03 Web Portfolio last updated: 2023.09

Contact

github stat

github_stat

leetcode stat

leetcode_stat

Hyeongmin Moon's Projects

autocrawler icon autocrawler

Google, Naver multiprocess image web crawler (Selenium)

blendgan icon blendgan

Official PyTorch implementation of "BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation" (NeurIPS 2021)

chatbot-with-translation icon chatbot-with-translation

Chatbot with Translation. Original input text is translated to english for the best performance of Chatbot, and translated back to original language.

ddetailer icon ddetailer

ddetailer with fixed dynamic prompt, wildcard. Also supports custom removal for Lora

fastchat-autogptq icon fastchat-autogptq

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and FastChat-T5.

leetcode icon leetcode

Collection of LeetCode questions to ace the coding interview! - Created using [LeetHub](https://github.com/QasimWani/LeetHub)

mae-pytorch icon mae-pytorch

Unofficial PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners

models icon models

Models and examples built with TensorFlow

onnx2keras icon onnx2keras

Convert ONNX model graph to Keras model format.

patrickstar icon patrickstar

PatrickStar enables Larger, Faster, Greener Pretrained Models for NLP. Democratize AI for everyone.

polygonobjectdetection icon polygonobjectdetection

This repository is based on Ultralytics/yolov5, with adjustments to enable polygon prediction boxes.

pulse icon pulse

PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.