Update app.py

app.py

@@ -37,7 +37,7 @@ model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
 
 # use quantization to lower GPU usage
 bnb_config = BitsAndBytesConfig(
-    load_in 4bit=True, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16
+    load_in_4bit=True, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16
 )
 
 tokenizer = AutoTokenizer.from_pretrained(model_id, token=token)