mmarch/text-generation-webui
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Fix GPTQ load_quant call on Windows

Browse source
This commit is contained in:
oobabooga 2023-03-13 12:07:02 -03:00
parent bdff37f0bb
commit 372363bc3d
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
modules/quantized_LLaMA.py
View file

@ -40,7 +40,7 @@ def load_quantized_LLaMA(model_name):
print(f"Could not find {pt_model}, exiting...") print(f"Could not find {pt_model}, exiting...")
exit() exit()
model = load_quant(path_to_model, str(pt_path), bits) model = load_quant(str(path_to_model), str(pt_path), bits)
# Multiple GPUs or GPU+CPU # Multiple GPUs or GPU+CPU
if shared.args.gpu_memory: if shared.args.gpu_memory: