Update app.py

app.py

@@ -36,6 +36,7 @@ device = "cuda" # for GPU usage or "cpu" for CPU usage
 tokenizer = AutoTokenizer.from_pretrained(MODEL)
 model = AutoModelForCausalLM.from_pretrained(
     MODEL,
+    torch_dtype=torch.bfloat16,
     low_cpu_mem_usage=True,
     device_map="auto")