From 372363bc3d5383d8351e45ee77323ba686a59769 Mon Sep 17 00:00:00 2001
From: oobabooga <112222186+oobabooga@users.noreply.github.com>
Date: Mon, 13 Mar 2023 12:07:02 -0300
Subject: [PATCH] Fix GPTQ load_quant call on Windows

---
 modules/quantized_LLaMA.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/modules/quantized_LLaMA.py b/modules/quantized_LLaMA.py
index e9352f90..a5757c68 100644
--- a/modules/quantized_LLaMA.py
+++ b/modules/quantized_LLaMA.py
@@ -40,7 +40,7 @@ def load_quantized_LLaMA(model_name):
         print(f"Could not find {pt_model}, exiting...")
         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
     if shared.args.gpu_memory: