Update app.py

app.py

@@ -21,6 +21,9 @@ try:
     tokenizer = AutoTokenizer.from_pretrained(model_id)
     tokenizer.model_max_length = 512
 
+    dummy_input = tokenizer("This is a test.", return_tensors="pt").to(model.device)
+    model.generate(input_ids=dummy_input.input_ids, return_dict=True)  # Dummy call
+
 except Exception as e:
     print(f"Error loading model: {e}")
     exit()
@@ -87,4 +90,4 @@ demo = gr.ChatInterface(
 )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()