Update app.py

app.py

@@ -10,7 +10,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
     device_map="auto",
-    torch_dtype=torch.bfloat16,
+    load_in_8bit=True
 )
 
 @spaces.GPU