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

cannot execute file: binary Format error for exec()

Open anonymouso5310 opened this issue 2 years ago • 3 comments

Hi i have an error when i try to install LLama when i have to quantize the model to 4-bits i got this error : Permission not granted so i've allowed it to be execute and now i have this error: cannot execute file: binary Format error for exec()

pls help

anonymouso5310 avatar Apr 25 '23 18:04 anonymouso5310

How did you compile llama.cpp? What compiler? Did you get any errors?

SlyEcho avatar Apr 25 '23 19:04 SlyEcho

i've used cmake and there is no errors

anonymouso5310 avatar Apr 25 '23 19:04 anonymouso5310

What was the command that you used to quantize?

It should be ./build/bin/quantize ./models/ggml-model-f16.bin ./models/ggml-model-q4_0.bin 2 or similar assuming you are in the llama.cpp root and that your CMake build dir is build

SlyEcho avatar Apr 25 '23 20:04 SlyEcho