Update app.py

app.py

@@ -27,7 +27,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_id, token= token)
 model = AutoModelForCausalLM.from_pretrained(model_id, token= token, torch_dtype=torch.bfloat16,    
                                              # attn_implementation="flash_attention_2",
                                              low_cpu_mem_usage=True,
-                                             device_map="cuda"
+                                             device_map="auto"
                                             )