try

app.py

@@ -9,12 +9,9 @@ For more information on `huggingface_hub` Inference API support, please check th
 # client = InferenceClient("EITD/lora_model", token=os.getenv("HF_TOKEN"))
 
 model_name = "EITD/lora_model"
-quantization_config = BitsAndBytesConfig(
-    load_in_4bit=True
-)
 model = AutoPeftModelForCausalLM.from_pretrained(
     model_name,
-    quantization_config=quantization_config
+    load_in_4bit = True,
 )
 tokenizer = AutoTokenizer.from_pretrained(model_name)