vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Fixed a typo and removed shell=True in the subprocess.run call

Browse source 
Fixed a typo regarding the new filenames of the quantized models and removed the shell=True parameter in the subprocess.run call as it was conflicting with the list of parameters.
This commit is contained in:
Gerardo Romero 2023-03-19 12:15:47 -06:00
parent 5d864c1d69
commit b802b788c4
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
quantize.py
View file

@ -104,7 +104,7 @@ def __run_quantize_script(script_path, f16_model_part_path):
f16 model to quantize.
"""
new_quantized_model_path = f16_model_part_path.replace("16", "q4_0")
new_quantized_model_path = f16_model_part_path.replace("f16", "q4_0")
subprocess.run(
[script_path, f16_model_part_path, new_quantized_model_path, "2"],
shell=True, check=True