#
Lists (32)
✔️ Annotation
Data annotation tools20 repositories
🖼️ Visualizations
Repos for visualizing, graphing, model interpretability tools... all that good stuff46 repositories
Adversarial
5 repositories
🗳️ Archived
Projects no longer active🎨 Color
39 repositories
🛢Data
Repos of datasets & data wrangling libs25 repositories
🎁 DBs
27 repositories
🎨 Design
3 repositories
🧨 Diffusion
Everything about diffusion models33 repositories
📚 Educational
Book, tutorial type materials50 repositories
👗 Fashion
53 repositories
Flow
flow based programming stuff11 repositories
🔔 Frameworks
5 repositories
🤡 Fun
Stuff just for fun32 repositories
Image Generation
generation, manipulation edits, style transfer, etc5 repositories
🪐 Jupyter
Jupyter notebook/lab extensions etc36 repositories
🇰🇷 Korean
mostly Korean NLP stuff98 repositories
Lists of lists
list of awesome-style lists22 repositories
🍎 mac
16 repositories
🧰 MLOps
20 repositories
💖 Most Used
Stuff that I use on an almost daily basis21 repositories
🏃 Optimization
Stuff for optimizing runtime etc33 repositories
OS alternatives
Open-Source alternatives to popular programs25 repositories
📝 Papers
AI Paper implementations official & other23 repositories
🔧 Processing & Calc
28 repositories
Scale
2 repositories
🔥 Streamlit
Streamlit components, tutorials, examples...142 repositories
Temp
3 repositories
💻 Terminal
Stuff to make your terminal pretty & useful commands41 repositories
📹 Video Generation
video prediction/generation papers.20 repositories
👀Watching
1 repository
🌐 Web/JS/UI
Javascript & Web & UI dev related stuff29 repositories
Starred repositories
3394
results
for source starred repositories
Clear filter
Code at data for "Explaining and Mitigating Crosslingual Tokenizer Inequities", published at NeurIPS 2025
🎒 Token-Oriented Object Notation (TOON) – JSON for LLM prompts at half the tokens. Spec, benchmarks & TypeScript implementation.
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
This is a package to fine-tune language models in order to create clustering-friendly embeddings.
Detection and automatic updating of Korean datasets uploaded to Hugging Face
Sample base images for Databricks Container Services
A very fast SIMD-first image comparison library (with nodejs API)
Unofficial implementation of Tiny Recursive Model (TRM), improvement to HRM from Sapient AI, by Alexia Jolicoeur-Martineau
Efficient RWKV inference engine. RWKV7 7.2B fp16 decoding 10250 tps @ single 5090.
Vocabulary Trimming (VT) is a model compression technique, which reduces a multilingual LM vocabulary to a target language by deleting irrelevant tokens from its vocabulary. This repository contain…
Python project to ship N8N execution data to Langfuse using OTEL API.
Ko-SyllaBERT: A Syllable-Based Efficient and Robust Korean Language Model for Real-World Noise and Typographical Errors
biasing the universal tokenizer and an attempt to optimize compression rates in multilingual compression
A simple tool for adapting a pretrained Huggingface model to a new vocabulary with (almost) no training.
A massively multilingual modern encoder language model
▁▅▆▃▅ Git quick statistics is a simple and efficient way to access various statistics in git repository.
Official code repo for the O'Reilly Book - "Hands-On Large Language Models"
Zero-Config Code Flow for Claude code & Codex
한국 서비스에 이용 가능한 Public API 모음 | Public APIs Available for Korean Services
An n8n community node that brings Langfuse observability to your OpenAI chat workflows.
AI Product Design Agent - Open Source
Train embedding and reranker models for retrieval tasks on Apple Silicon with MLX
GraphER: A Structure-aware Text-to-Graph Model for Entity and Relation Extraction
[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'