Download the EXE from here, select the one that matches your CPU AVX, AVX2 or AVX512:
https://github.com/ggerganov/llama.cpp/releases
Download the data from here:
https://huggingface.co/eachadea/ggml-vicuna-13b-4bit/resolve/main/ggml-vicuna-13b-4bit.bin
Create this run.bat to execute it:
- Code: Select all Expand view RUN
- title llama.cpp
:start
main -i --interactive-first -r "### Human:" -t 8 --temp 0 -c 2048 -n -1 --ignore-eos --repeat_penalty 1.2 --instruct -m models/llama-7B/ggml-vicuna-13b-4bit.bin
pause
goto start