Update app.py

app.py

@@ -39,6 +39,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
     device_map="auto",
+    torch_dtype=torch.bfloat16,
     attn_implementation="flash_attention_2",
     # quantization_config=quantization_config,
 )