Update app.py

app.py

@@ -33,11 +33,6 @@ def model_loading_pipeline():
         model=model_id,
         model_kwargs={
             "torch_dtype": torch.float16,
-            "load_in_4bits": True,
-            "quantization_config": BitsAndBytesConfig(
-                load_in_4bit=True,
-                bnb_4bit_compute_dtype=torch.float16
-            ),
         },
         streamer=streamer,
     )