Update app.py

app.py

@@ -12,15 +12,12 @@ token = os.environ.get("HF_TOKEN")
 
 model_id = "google/shieldgemma-2b"
 
-# Use quantization to lower GPU usage
+# 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)
+tokenizer = AutoTokenizer.from_pretrained(model_id,token=token)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
     torch_dtype=torch.bfloat16,