Update app.py

app.py

@@ -9,7 +9,7 @@ import nncf
 import huggingface_hub as hf_hub
 # 初始化 OpenVINO 模型
 model_id = "Qwen/Qwen3-1.7B"
-optimized_model_path = "ov"
+model_path = "ov"
 '''
 import subprocess
 
@@ -38,13 +38,14 @@ hf_hub.snapshot_download(model_id, local_dir=model_path)
 model_path = "ov"
 pipe = ov_genai.LLMPipeline(model_path, "CPU")
 '''
+
 model = OVModelForCausalLM.from_pretrained(
-    model_path,
+    model_id,
     quantization_config=OVWeightQuantizationConfig(bits=4, asym=True, ratio=0.8, dataset="ptb"),
 )
 
 # save the model after optimization
-model.save_pretrained(optimized_model_path)
+model.save_pretrained(model_path)
 
 #pipe.start_chat()