leemgs
Geunsik Lim has been working as a system software engineer for deploying embedded devices at Samsung Electronics.
Samsung ElectronicsSeoul, South korea
Pinned Repositories
auto-freedns-afraid-org
Automatically log-in for account and sub-domain at freedns.afraid.org
dclab4u.github.io
DC Lab Homepage
github-issues-import-ng
:wrench: The github-issues-import-ng repository is to import issues and pull requests from one repository into another one at once.
leemgs.github.io
GitHub repository for Geunsik's Homepage
music-genre-class-f1-score
:pear: [산업인공지능: Term Project] Music Genres Classification (Precision, Recall, and F1-Score)
samsung-s3c6410-android.1.0
samsung-s3c6410-android.1.0 (2.6.24 base)
SM-N9600
Galaxy Note 9 (SM-N9600), 2018, https://opensource.samsung.com/uploadList
SM-N970F
Galaxy Note 10 (SM-N970F), 2019, https://opensource.samsung.com/uploadList
SM-N980F
Galaxy Note 20 (SM-N980F), 2020, https://opensource.samsung.com/uploadList
smart-video-workshop
leemgs's Repositories
leemgs/leemgs.github.io
GitHub repository for Geunsik's Homepage
leemgs/mytest
leemgs/dclab4u.github.io
DC Lab Homepage
leemgs/agensgraph
AgensGraph, a transactional graph database based on PostgreSQL
leemgs/atlassian-python-api
Atlassian Python REST API wrapper
leemgs/Awesome-Code-LLM
leemgs/axolotl
Go ahead and axolotl questions
leemgs/CodeChain
Official code for the paper "CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules"
leemgs/CodeFuse-ModelCache
A LLM semantic caching system aiming to enhance user experience by reducing response time via cached query-result pairs.
leemgs/CodeMMLU
leemgs/FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
leemgs/foundation
leemgs/g6
leemgs/generative-ai-android
Google AI SDK for Android
leemgs/GPTCache
Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
leemgs/k8sgpt
Giving Kubernetes Superpowers to everyone
leemgs/llama-recipes
Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.
leemgs/llama.cpp
Port of Facebook's LLaMA model in C/C++
leemgs/mixtral-offloading
Run Mixtral-8x7B models in Colab or consumer desktops
leemgs/OpenDevin
🐚 OpenDevin: Code Less, Make More
leemgs/photorama
Photo Gallery
leemgs/promptfoo
Test your prompts, agents, and RAGs. Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line and CI/CD integration.
leemgs/SE_ProDS
leemgs/tegon
Tegon is an open-source, AI-first alternative to Jira, Linear
leemgs/tinyfilemanager
Single-file PHP file manager, browser and manage your files efficiently and easily with tinyfilemanager
leemgs/tree-sitter-kotlin
Kotlin grammar for Tree-sitter
leemgs/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
leemgs/vscode-languagedetection
An npm package that uses ML to detect source code languages
leemgs/with-people
Photo collection to archive memorable recollection in my life.
leemgs/zoekt
Fast trigram based code search