rename method

modules/models.py

@@ -89,9 +89,9 @@ def load_model(model_name):
 
     # Quantized model
     elif shared.args.gptq_bits > 0:
-        from modules.quant_loader import load_quant
+        from modules.quant_loader import load_quantized
 
-        model = load_quant(model_name, shared.args.gptq_model_type)
+        model = load_quantized(model_name, shared.args.gptq_model_type)
 
     # Custom
     else:

modules/quant_loader.py

@@ -10,7 +10,7 @@ sys.path.insert(0, str(Path("repositories/GPTQ-for-LLaMa")))
 
 
 # 4-bit LLaMA
-def load_quant(model_name, model_type):
+def load_quantized(model_name, model_type):
     if model_type == 'llama':
         from llama import load_quant
     elif model_type == 'opt':