Update app.py

app.py

@@ -26,7 +26,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
     device_map="auto",
-    torch_dtype=torch.float32
+    torch_dtype=torch.float16
 )
 
 @spaces.GPU