Fix for Falcon image-to-text crash

[schoi-habana]

  File "/root/optimum-habana/examples/image-to-text/run_pipeline.py", line 414, in <module>
    main()
  File "/root/optimum-habana/examples/image-to-text/run_pipeline
  .py", line 375, in main
    generator(images, prompt=args.prompt, batch_size=args.batch_size, generate_kwargs=generate_kwargs)
  File "/usr/local/lib/python3.10/dist-packages/transformers/pipelines/image_to_text.py", line 137, in call
    return super().call(inputs, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/transformers/pipelines/base.py", line 1343, in call
    outputs = list(final_iterator)
  File "/usr/local/lib/python3.10/dist-packages/transformers/pipelines/pt_utils.py", line 124, in next
    item = next(self.iterator)
  File "/usr/local/lib/python3.10/dist-packages/transformers/pipelines/pt_utils.py", line 124, in next
    item = next(self.iterator)
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/data/dataloader.py", line 708, in next
    data = self._next_data()
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/data/dataloader.py", line 764, in _next_data
    data = self._dataset_fetcher.fetch(index)  # may raise StopIteration
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/data/_utils/fetch.py", line 52, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/data/_utils/fetch.py", line 52, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/usr/local/lib/python3.10/dist-packages/transformers/pipelines/pt_utils.py", line 19, in getitem
    processed = self.process(item, **self.params)
  File "/root/optimum-habana/examples/image-to-text/run_pipeline.py", line 368, in preprocess
    model_inputs = processor(images=image, text=prompt, return_tensors=self.framework, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/transformers/models/llava_next/processing_llava_next.py", line 162, in call
    num_image_tokens = self._get_number_of_features(orig_height, orig_width, height, width)
  File "/usr/local/lib/python3.10/dist-packages/transformers/models/llava_next/processing_llava_next.py", line 181, in _get_number_of_features
    patches_height = height // self.patch_size
TypeError: unsupported operand type(s) for //: 'int' and 'NoneType' ```

This happens because of a change in LlavaNextProcessor in Transformers.
In Transformers 4.45.2, if self.patch_size was None, the code skipped the part that caused the error. But in later versions, it no longer skips it.
Other Llava-Next models didn’t run into this error, so the fix is limited to falcon-11b-vlm.

## Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
- [ ] Did you make sure to update the documentation with your changes?
- [ ] Did you write any new necessary tests?

[regisss]

LGTM!