Uniformize kwargs for LLaVa processor and update docs (#32858)

* Uniformize kwargs for LlaVa and update docs

* Change order of processor inputs in docstring

* Improve BC support for reversed images and text inputs

* cleanup llava processor call docstring

* Add encoded inputs as valid text inputs in reverse input check, add deprecation version in warning

* Put function check reversed images text outside base processor class

* Refactor _validate_images_text_input_order

* Add ProcessingUtilTester

* fix processing and test_processing

tests/models/llava/test_processor_llava.py

@@ -11,18 +11,43 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+import shutil
+import tempfile
 import unittest
 
-from transformers.testing_utils import require_vision
+from transformers import AutoProcessor, AutoTokenizer, LlamaTokenizerFast, LlavaProcessor
+from transformers.testing_utils import require_torch, require_vision
 from transformers.utils import is_vision_available
 
+from ...test_processing_common import ProcessorTesterMixin
+
 
 if is_vision_available():
-    from transformers import AutoTokenizer, LlavaProcessor
+    from transformers import CLIPImageProcessor
 
 
 @require_vision
-class LlavaProcessorTest(unittest.TestCase):
+class LlavaProcessorTest(ProcessorTesterMixin, unittest.TestCase):
+    processor_class = LlavaProcessor
+
+    def setUp(self):
+        self.tmpdirname = tempfile.mkdtemp()
+        image_processor = CLIPImageProcessor(do_center_crop=False)
+        tokenizer = LlamaTokenizerFast.from_pretrained("huggyllama/llama-7b")
+
+        processor = LlavaProcessor(image_processor=image_processor, tokenizer=tokenizer)
+
+        processor.save_pretrained(self.tmpdirname)
+
+    def get_tokenizer(self, **kwargs):
+        return AutoProcessor.from_pretrained(self.tmpdirname, **kwargs).tokenizer
+
+    def get_image_processor(self, **kwargs):
+        return AutoProcessor.from_pretrained(self.tmpdirname, **kwargs).image_processor
+
+    def tearDown(self):
+        shutil.rmtree(self.tmpdirname)
+
     def test_can_load_various_tokenizers(self):
         for checkpoint in ["Intel/llava-gemma-2b", "llava-hf/llava-1.5-7b-hf"]:
             processor = LlavaProcessor.from_pretrained(checkpoint)
@@ -45,3 +70,29 @@ class LlavaProcessorTest(unittest.TestCase):
 
         formatted_prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
         self.assertEqual(expected_prompt, formatted_prompt)
+
+    @require_torch
+    @require_vision
+    def test_unstructured_kwargs_batched(self):
+        if "image_processor" not in self.processor_class.attributes:
+            self.skipTest(f"image_processor attribute not present in {self.processor_class}")
+        image_processor = self.get_component("image_processor")
+        tokenizer = self.get_component("tokenizer")
+
+        processor = self.processor_class(tokenizer=tokenizer, image_processor=image_processor)
+        self.skip_processor_without_typed_kwargs(processor)
+
+        input_str = ["lower newer", "upper older longer string"]
+        image_input = self.prepare_image_inputs() * 2
+        inputs = processor(
+            images=image_input,
+            text=input_str,
+            return_tensors="pt",
+            size={"height": 214, "width": 214},
+            padding="longest",
+            max_length=76,
+        )
+
+        self.assertEqual(inputs["pixel_values"].shape[2], 214)
+
+        self.assertEqual(len(inputs["input_ids"][0]), 5)