"description":"Nodes: ExLlama Loader, ExLlama Generator. <BR>Used to load 4-bit GPTQ Llama/2 models. You can find a lot of them over at <a href='https://huggingface.co/TheBloke'>https://huggingface.co/TheBloke</a><p style='background-color: black; color: red;'>NOTE: You need to manually install a pip package that suits your system. For example. If your system is 'Python3.10 + Windows + CUDA 11.8' then you need to install 'exllama-0.0.17+cu118-cp310-cp310-win_amd64.whl'. Available package files are <a href='https://github.com/jllllll/exllama/releases'>here</a>."