Update app.py

app.py

@@ -3,10 +3,14 @@ import openvino_genai as ov_genai
 import queue
 import threading
 import time
+from optimum.intel import OVModelForCausalLM, OVWeightQuantizationConfig
+import nncf
 
 import huggingface_hub as hf_hub
 # 初始化 OpenVINO 模型
-
+model_id = "Qwen/Qwen3-1.7B"
+optimized_model_path = "ov"
+'''
 import subprocess
 
 subprocess.run([
@@ -17,7 +21,7 @@ subprocess.run([
     "--quant-mode", "int4_f8e4m3",
     "ov"
 ])
-
+'''
 
 '''
 model_id = "OpenVINO/Qwen2.5-7B-Instruct-int4-ov"
@@ -30,9 +34,18 @@ config.top_k = 30;
 
 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,
+    quantization_config=OVWeightQuantizationConfig(bits=4, asym=True, ratio=0.8, dataset="ptb"),
+)
+
+# save the model after optimization
+model.save_pretrained(optimized_model_path)
+
 #pipe.start_chat()
 
 def start_chat():