llama.cpp icon indicating copy to clipboard operation
llama.cpp copied to clipboard

Published 20 hours ago • verified publisher icon ggml-org

Fails to run quantize command

Open jayliang701 opened this issue 1 year ago • 1 comments

Hi, this project looks great! But I got the below error.

Mackbook Air M1

./build/bin/quantize ./models/7B/ggml-model-f16.bin ./models/7B/ggml-model-q4_0.bin 2
zsh: killed     ./build/bin/quantize ./models/7B/ggml-model-f16.bin  2

I have tried to install cmake and re-build, didn't work.

Any idea?

jayliang701 avatar Apr 12 '23 16:04 jayliang701

Getting the same issue. I think I've identified the issue. Working on a fix

arikpoz avatar Apr 12 '23 21:04 arikpoz

Presumably solved by #927, closing.

sw avatar Apr 22 '23 17:04 sw