Update app.py

app.py

@@ -33,7 +33,7 @@ if not torch.cuda.is_available():
     DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
 
 if torch.cuda.is_available():
-    model_id = "Qwen/Qwen2.5-0.5B-Instruct"
+    model_id = "Qwen/Qwen2.5-3B-Instruct"
     model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")
     tokenizer = AutoTokenizer.from_pretrained(model_id)
     tokenizer.use_default_system_prompt = False