OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset

Faster Whisper transcription with CTranslate2

Code and documentation to train Stanford's Alpaca models, and generate the data.

LLM inference in C/C++

Port of OpenAI's Whisper model in C/C++

Streamlit LLM app examples for getting started

🦜🔗 Build context-aware reasoning applications