KillianLucas / ooba

Run language models on consumer hardware.

A headless Oobabooga wrapper.

pip install ooba

import ooba

path = ooba.download("https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF")

llm = ooba.llm(path)

messages = [{"role": "user", "content": "Hi Mistral."}]

for token in llm.chat(messages):
    print(token)

ooba.product.demo.mp4