Update app.py

app.py

@@ -22,7 +22,7 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 HF_TOKEN = os.getenv("HF_TOKEN")
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
-model_name = "Qwen/Qwen2.5-7B-Instruct"
+model_name = "Qwen/Qwen2.5-3B-Instruct"
 
 model = AutoModelForCausalLM.from_pretrained(
     model_name,