Update app_v2.py

app_v2.py

@@ -11,7 +11,7 @@ quantized_model_dir = "./Jackson2-4bit-128g-GPTQ"
 os.makedirs(quantized_model_dir, exist_ok=True)
 
 # Quantization configuration
-quantize_config = BaseQuantizeConfig(bits=4, group_size=128, desc_act=False)
+quantize_config = BaseQuantizeConfig(bits=4, group_size=128, damp_percent=0.01, desc_act=False)
 
 # Load the model using from_quantized
 model = AutoGPTQForCausalLM.from_quantized(