[Tests] Clean up test cases for few models (#38315)

* Update tests

* revert aria change

* too slow hence revert

tests/models/qwen2_5_omni/test_processor_qwen2_5_omni.py

@@ -204,8 +204,7 @@ class Qwen2_5OmniProcessorTest(ProcessorTesterMixin, unittest.TestCase):
     @classmethod
     def setUpClass(cls):
         cls.tmpdirname = tempfile.mkdtemp()
-        processor_kwargs = cls.prepare_processor_dict()
-        processor = Qwen2_5OmniProcessor.from_pretrained("Qwen/Qwen2.5-Omni-7B", **processor_kwargs)
+        processor = Qwen2_5OmniProcessor.from_pretrained("Qwen/Qwen2.5-Omni-7B")
         processor.save_pretrained(cls.tmpdirname)
 
     def get_tokenizer(self, **kwargs):
@@ -220,11 +219,8 @@ class Qwen2_5OmniProcessorTest(ProcessorTesterMixin, unittest.TestCase):
     def get_feature_extractor(self, **kwargs):
         return AutoProcessor.from_pretrained(self.tmpdirname, **kwargs).feature_extractor
 
-    @staticmethod
-    def prepare_processor_dict():
-        return {
-            "chat_template": "{% set audio_count = namespace(value=0) %}{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_bos|><|IMAGE|><|vision_eos|>{% elif content['type'] == 'audio' or 'audio' in content or 'audio_url' in content %}{% set audio_count.value = audio_count.value + 1 %}{% if add_audio_id %}Audio {{ audio_count.value }}: {% endif %}<|audio_bos|><|AUDIO|><|audio_eos|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_bos|><|VIDEO|><|vision_eos|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
-        }
+    def get_processor(self, **kwargs):
+        return AutoProcessor.from_pretrained(self.tmpdirname, **kwargs)
 
     @classmethod
     def tearDownClass(cls):

tests/models/qwen2_5_vl/test_processor_qwen2_5_vl.py

@@ -58,11 +58,8 @@ class Qwen2_5_VLProcessorTest(ProcessorTesterMixin, unittest.TestCase):
     def get_video_processor(self, **kwargs):
         return AutoProcessor.from_pretrained(self.tmpdirname, **kwargs).video_processor
 
-    @staticmethod
-    def prepare_processor_dict():
-        return {
-            "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
-        }  # fmt: skip
+    def get_processor(self, **kwargs):
+        return AutoProcessor.from_pretrained(self.tmpdirname, **kwargs)
 
     @classmethod
     def tearDownClass(cls):
@@ -340,12 +337,7 @@ class Qwen2_5_VLProcessorTest(ProcessorTesterMixin, unittest.TestCase):
         self.assertEqual(len(out_dict_with_video[self.videos_input_name]), 160)
 
     def test_kwargs_overrides_custom_image_processor_kwargs(self):
-        processor_components = self.prepare_components()
-        processor_components["image_processor"] = self.get_component("image_processor")
-        processor_components["tokenizer"] = self.get_component("tokenizer")
-        processor_kwargs = self.prepare_processor_dict()
-
-        processor = self.processor_class(**processor_components, **processor_kwargs, use_fast=True)
+        processor = self.get_processor()
         self.skip_processor_without_typed_kwargs(processor)
 
         input_str = self.prepare_text_inputs()

tests/models/qwen2_audio/test_processor_qwen2_audio.py

@@ -36,8 +36,7 @@ class Qwen2AudioProcessorTest(ProcessorTesterMixin, unittest.TestCase):
         cls.checkpoint = "Qwen/Qwen2-Audio-7B-Instruct"
         cls.tmpdirname = tempfile.mkdtemp()
 
-        processor_kwargs = cls.prepare_processor_dict()
-        processor = Qwen2AudioProcessor.from_pretrained(cls.checkpoint, **processor_kwargs)
+        processor = Qwen2AudioProcessor.from_pretrained(cls.checkpoint)
         processor.save_pretrained(cls.tmpdirname)
         cls.audio_token = processor.audio_token
 
@@ -47,16 +46,13 @@ class Qwen2AudioProcessorTest(ProcessorTesterMixin, unittest.TestCase):
     def get_audio_processor(self, **kwargs):
         return AutoProcessor.from_pretrained(self.tmpdirname, **kwargs).audio_processor
 
+    def get_processor(self, **kwargs):
+        return AutoProcessor.from_pretrained(self.tmpdirname, **kwargs)
+
     @classmethod
     def tearDownClass(cls):
         shutil.rmtree(cls.tmpdirname, ignore_errors=True)
 
-    @staticmethod
-    def prepare_processor_dict():
-        return {
-            "chat_template": "{% set audio_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if 'audio' in content or 'audio_url' in content or content['type'] == 'audio' %}{% set audio_count.value = audio_count.value + 1 %}Audio {{ audio_count.value }}: <|audio_bos|><|AUDIO|><|audio_eos|>\n{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
-        }
-
     def test_can_load_various_tokenizers(self):
         processor = Qwen2AudioProcessor.from_pretrained(self.checkpoint)
         tokenizer = AutoTokenizer.from_pretrained(self.checkpoint)

tests/models/qwen2_vl/test_processor_qwen2_vl.py

@@ -61,9 +61,8 @@ class Qwen2VLProcessorTest(ProcessorTesterMixin, unittest.TestCase):
     def get_video_processor(self, **kwargs):
         return AutoProcessor.from_pretrained(self.tmpdirname, **kwargs).video_processor
 
-    @staticmethod
-    def prepare_processor_dict():
-        return {"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"}  # fmt: skip
+    def get_processor(self, **kwargs):
+        return AutoProcessor.from_pretrained(self.tmpdirname, **kwargs)
 
     @classmethod
     def tearDownClass(cls):
@@ -406,12 +405,7 @@ class Qwen2VLProcessorTest(ProcessorTesterMixin, unittest.TestCase):
         self.assertEqual(len(out_dict_with_video[self.videos_input_name]), 21960)
 
     def test_kwargs_overrides_custom_image_processor_kwargs(self):
-        processor_components = self.prepare_components()
-        processor_components["image_processor"] = self.get_component("image_processor")
-        processor_components["tokenizer"] = self.get_component("tokenizer")
-        processor_kwargs = self.prepare_processor_dict()
-
-        processor = self.processor_class(**processor_components, **processor_kwargs, use_fast=True)
+        processor = self.get_processor()
         self.skip_processor_without_typed_kwargs(processor)
 
         input_str = self.prepare_text_inputs()