qresearch

/

llama-3-vision-alpha

like 60

Follow

qresearch 12

I'm trying to run the model after following all of the specified instructions, but I keep on getting an import error: "ImportError: Using bitsandbytes 8-bit quantization requires Accelerate: pip install accelerate and the latest version of bitsandbytes: pip install -i https://pypi.org/simple/ bitsandbytes" even though I have these installed and have tried deleting and reinstalling them.

OS: Ubuntu 23.10
Hardware: AMD Ryzen 7 Pro
Python 3.11.6
pip 23.2

Any help would be greatly appreciated!