Update app.py

app.py

@@ -24,7 +24,7 @@ if not torch.cuda.is_available():
 
 if torch.cuda.is_available():
     model_id = "hon9kon9ize/CantoneseLLMChat-preview20240326"
-    model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype=torch.bfloat16,)
+    model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
     model = torch.compile(model)
     tokenizer = AutoTokenizer.from_pretrained(model_id)
     tokenizer.use_default_system_prompt = False