Update app.py

app.py

@@ -47,8 +47,7 @@ class DocumentRetrievalAndGeneration:
             bnb_4bit_quant_type="nf4",
             bnb_4bit_compute_dtype=torch.bfloat16
         )
-        device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-        model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config).to(device)
+        model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config)
         tokenizer = AutoTokenizer.from_pretrained(model_id)
         generate_text = pipeline(
             model=model,