Kanana: Compute-efficient Bilingual Language Models

FUSE-based file system backed by Amazon S3

Modern CSS framework based on Flexbox

주요 LLM 트위터 인사들의 내용을 긱뉴스 형식으로 번역.

Make running benchmark simple yet maintainable, again. Now only supports Korean-based cross-encoder.

A collection of community made keymaps for PlayCover.

Lightweight tool to identify Data Contamination in LLMs evaluation

An extremely fast Python linter and code formatter, written in Rust.

A benchmark dataset for evaluating LLM's SVG editing capabilities

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

Janus-Series: Unified Multimodal Understanding and Generation Models

Fully open reproduction of DeepSeek-R1

ezkl is an engine for doing inference for deep learning models and other computational graphs in a zk-snark (ZKML). Use it from Python, Javascript, or the command line.

Efficient Zero-Knowledge Proofs for LoRA Verification

🏭 The most lightweight, customizable React markdown component.

Dummy project to create an English/French translation service using Hugging Face, Docker and such.

A container registry backed by Workers and R2.

g2pK: g2p module for Korean

A tool for manual conversion of BGE-M3 models with preserved trainable variables and direct control over model outputs.

Undergraduate Course Explorer for KAIST

Safe eval runtime

A simple web server written in Lua

The AMM Laboratory

The most powerful wallet for the Cosmos ecosystem and the Interchain

Make use of Huggingface Transformers Trainer for customized structures

Ultra fast asyncio event loop.

All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more.

🛰️ An approximate nearest-neighbor search library for Python and Java with a focus on ease of use, simplicity, and deployability.

Scalable toolkit for efficient model alignment