Update app.py

app.py

@@ -39,13 +39,15 @@ model_path = "ov"
 pipe = ov_genai.LLMPipeline(model_path, "CPU")
 '''
 
-model = OVModelForCausalLM.from_pretrained(
+pipe = OVModelForCausalLM.from_pretrained(
     model_id,
-    quantization_config=OVWeightQuantizationConfig(bits=4, asym=True, ratio=0.8, dataset="ptb"),
+    export=True,
+    quantization_config=OVWeightQuantizationConfig(bits=4),
 )
 
+
 # save the model after optimization
-model.save_pretrained(model_path)
+#pipe.save_pretrained(model_path)
 
 #pipe.start_chat()