That was true until 2 days ago :)
The repo has now been updated with requantized models that work with the latest version, so you don't need to do that any more.
https://huggingface.co/TheBloke/gpt4-x-vicuna-13B-GGML/commi...
The repo has now been updated with requantized models that work with the latest version, so you don't need to do that any more.
https://huggingface.co/TheBloke/gpt4-x-vicuna-13B-GGML/commi...