Update app.py

app.py

@@ -85,11 +85,12 @@ tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 if tokenizer.pad_token is None:
     tokenizer.pad_token = tokenizer.eos_token
     tokenizer.pad_token_id = tokenizer.eos_token_id
-    model = AutoModelForCausalLM.from_pretrained(
-    MODEL_ID,
-    device_map="auto",
-    quantization_config=quantization_config,
-    torch_dtype=torch.bfloat16
+    
+model = AutoModelForCausalLM.from_pretrained(
+MODEL_ID,
+device_map="auto",
+quantization_config=quantization_config,
+torch_dtype=torch.bfloat16
 )
 
 # Create Gradio interface