- Seoul, Republic of Korea
-
14:26
(UTC +09:00) - velog.io/@khs0415p/posts
Stars
🦛 CHONK your texts with Chonkie ✨ - The no-nonsense RAG chunking library
A vector search SQLite extension that runs anywhere!
CLI for SQLite Databases with auto-completion and syntax highlighting
Jan is an open source alternative to ChatGPT that runs 100% offline on your computer. Multiple engine support (llama.cpp, TensorRT-LLM)
AirLLM 70B inference with single 4GB GPU
Efficient Triton Kernels for LLM Training
💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows
Fast, Accurate, Lightweight Python library to make State of the Art Embedding
A framework for few-shot evaluation of language models.
Experimental ground for optimizing memory of pytorch models
A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.
Training small GPT-2 style models using Kolmogorov-Arnold networks.
Kolmogorov-Arnold Networks (KAN) using Chebyshev polynomials instead of B-splines.
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
🦜🔗 Build context-aware reasoning applications
State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.
Efficient Infinite Context Transformers with Infini-attention Pytorch Implementation + QwenMoE Implementation + Training Script + 1M context keypass retrieval
This is the code for our KILT leaderboard submissions (KGI + Re2G models).
Korean Multi-task Instruction Tuning
Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.
An awesome & curated list of best LLMOps tools for developers
📋 A list of open LLMs available for commercial use.
👦 👧 Technical-Interview guidelines written for those who started studying programming. I wish you all the best. 👾