Update app.py

app.py

@@ -9,9 +9,10 @@ tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=True)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
     device_map="auto",
-    torch_dtype=torch.float16,
     trust_remote_code=True,
-    revision="main"
+    revision="main",
+    torch_dtype=torch.float16,
+    low_cpu_mem_usage=True
 )
 
 pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)