Update app.py

app.py

@@ -10,7 +10,7 @@ device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name).to(device)
+model = AutoModelForCausalLM.from_pretrained(model_name)
 
 def respond(
     message: str,