tranformers v4.54 compatibility

processing_maira2.py

@@ -11,7 +11,7 @@ from transformers import BaseImageProcessor, LlavaProcessor, PreTrainedTokenizer
 from transformers.feature_extraction_utils import BatchFeature
 from transformers.image_utils import ImageInput, get_image_size, to_numpy_array
 from transformers.models.llava.processing_llava import LlavaProcessorKwargs
-from transformers.processing_utils import Unpack, _validate_images_text_input_order
+from transformers.processing_utils import Unpack
 from transformers.tokenization_utils_base import PreTokenizedInput, TextInput
 
 
@@ -696,9 +696,6 @@ class Maira2Processor(LlavaProcessor):
         if images is None and text is None:
             raise ValueError("You have to specify at least one of `images` or `text`.")
 
-        # check if images and text inputs are reversed for BC
-        images, text = _validate_images_text_input_order(images, text)
-
         output_kwargs = self._merge_kwargs(
             LlavaProcessorKwargs,
             tokenizer_init_kwargs=self.tokenizer.init_kwargs,