Update processing_phi3_v.py

processing_phi3_v.py

@@ -328,13 +328,13 @@ class Phi3VProcessor(ProcessorMixin):
  self.img_tokens = [f"<|image_{i + 1}|>" for i in range(1000000)]
 
  def __call__(
- self,
- text: Union[TextInput, List[TextInput]],
- images: ImageInput = None,
- padding: Union[bool, str, PaddingStrategy] = False,
- truncation: Union[bool, str, TruncationStrategy] = None,
- max_length=None,
- return_tensors: Optional[Union[str, TensorType]] = TensorType.PYTORCH,
+ self,
+ text: Union[TextInput, List[TextInput]],
+ images: ImageInput = None,
+ padding: Union[bool, str, PaddingStrategy] = False,
+ truncation: Union[bool, str, TruncationStrategy] = None,
+ max_length=None,
+ return_tensors: Optional[Union[str, TensorType]] = TensorType.PYTORCH,
  ) -> BatchFeature:
  """
  Main method to prepare for the model one or several sequences(s) and image(s). This method forwards the `text`
@@ -415,11 +415,9 @@ class Phi3VProcessor(ProcessorMixin):
  def get_special_image_token_id(self):
  return self.tokenizer.convert_tokens_to_ids(self.special_image_token)
 
- def _convert_images_texts_to_inputs(self, images, texts, padding=False, truncation=None, max_length=None,
- return_tensors=None):
+ def _convert_images_texts_to_inputs(self, images, texts, padding=False, truncation=None, max_length=None, return_tensors=None):
  if not len(images):
- model_inputs = self.tokenizer(texts, return_tensors=return_tensors, padding=padding, truncation=truncation,
- max_length=max_length)
+ model_inputs = self.tokenizer(texts, return_tensors=return_tensors, padding=padding, truncation=truncation, max_length=max_length)
  return BatchFeature(data={**model_inputs})
 
  pattern = r"<\|image_\d+\|>"