Roo Code gives you a whole dev team of AI agents in your code editor.

Run GGUF models easily with a KoboldAI UI. One File. Zero Install.

Deploy serverless containers to the cloud from your command line

Doing simple retrieval from LLM models at various context lengths to measure accuracy

Llama 2 Everywhere (L2E)

Ongoing research training transformer language models at scale, including: BERT & GPT-2

Python and NodeJS packages that monitors OpenAI API calls and send OpenAI usage metrics and logs to Grafana Cloud

a claude code clone (learning project)

『밑바닥부터 시작하는 딥러닝 1(리마스터판)』(한빛미디어, 2025)

Ongoing research training transformer models at scale

Install and debug iPhone apps from the command line, without using Xcode

Inference code for Mistral and Mixtral hacked up into original Llama implementation

Inference Llama 2 in one file of pure Rust 🦀

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Managing your machine learning lifecycle with MLflow and Amazon SageMaker

Transformer related optimization, including BERT, GPT

Personal fork from NVIDIA Deep Learning Examples

Python tools for NVIDIA Profiler

Painless middleware chaining for Go

Jupyter notebook with Python3 and PHP

📚 Go 언어 스타일가이드

🔧 .files, including ~/.macos — sensible hacker defaults for macOS

Short tutorial for TensorFlow, designed to be presented in-person

Chrome Apps

Kernel extension to disable anti-debug tricks and other useful XNU "features"

Sapus Tongue project