Update app.py

app.py

@@ -18,14 +18,6 @@ load_in_4bit = True  # Use 4-bit quantization to reduce memory usage
 
 peft_model_name = "limitedonly41/website_qwen2_7b_2"
 
-# Load the model and tokenizer during initialization (in the main process)
-model, tokenizer = FastLanguageModel.from_pretrained(
-    model_name=peft_model_name,
-    max_seq_length=max_seq_length,
-    dtype=dtype,
-    load_in_4bit=load_in_4bit,
-)
-FastLanguageModel.for_inference(model)  # Enable native 2x faster inference
 
 
 def fetch_data(url):
@@ -110,6 +102,18 @@ def classify_website(url):
 
     global model, tokenizer  # Declare model and tokenizer as global variables
 
+    if model is None or tokenizer is None:
+    
+        # Load the model and tokenizer during initialization (in the main process)
+        model, tokenizer = FastLanguageModel.from_pretrained(
+            model_name=peft_model_name,
+            max_seq_length=max_seq_length,
+            dtype=dtype,
+            load_in_4bit=load_in_4bit,
+        )
+        FastLanguageModel.for_inference(model)  # Enable native 2x faster inference
+
+    
     urls = [url]
     results_shop = main(urls)