Hi there, I’ve recently installed Llama with GPT4ALL and I know how to load single bin files into it but I recently came across this model which I want to try but it has two bin files.
In the past when I have tried models which use two or more bin files, they never seem to work in GPT4ALL / Llama and I’m completely confused.
This is the model I want to try out… I assume I can use Llama.cpp to run it? I am very confused. Help!!!
https://huggingface.co/mosaicml/mpt-7b-storywriter/discussions/14
This is my llama run.bat file
title llama.cpp
:start
set GPU=1
main -i --interactive-first -t 8 -r “### Human:” --temp 0 -c 2048 -n -1 --ignore-eos --repeat_penalty 1.2 --instruct -m ggml-vic13b-uncensored-q5_1.bin
pause
goto start