Update tiny model info. and pipeline testing (#25213)

* update tiny_model_summary.json

* update

* update

* update

---------
Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>

tests/models/falcon/test_modeling_falcon.py

@@ -278,9 +278,9 @@ class FalconModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMix
     pipeline_model_mapping = (
         {
             "feature-extraction": FalconModel,
+            "question-answering": FalconForQuestionAnswering,
             "text-classification": FalconForSequenceClassification,
             "text-generation": FalconForCausalLM,
-            "question-answering": FalconForQuestionAnswering,
             "token-classification": FalconForTokenClassification,
             "zero-shot": FalconForSequenceClassification,
         }

tests/models/mpt/test_modeling_mpt.py

@@ -362,7 +362,16 @@ class MptModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin,
     test_torchscript = False
     test_head_masking = False
     pipeline_model_mapping = (
-        {"feature-extraction": MptModel, "text-generation": MptForCausalLM} if is_torch_available() else {}
+        {
+            "feature-extraction": MptModel,
+            "question-answering": MptForQuestionAnswering,
+            "text-classification": MptForSequenceClassification,
+            "text-generation": MptForCausalLM,
+            "token-classification": MptForTokenClassification,
+            "zero-shot": MptForSequenceClassification,
+        }
+        if is_torch_available()
+        else {}
     )
 
     def setUp(self):

tests/models/mra/test_modeling_mra.py

@@ -22,6 +22,7 @@ from transformers.testing_utils import require_torch, slow, torch_device
 
 from ...test_configuration_common import ConfigTester
 from ...test_modeling_common import ModelTesterMixin, floats_tensor, ids_tensor, random_attention_mask
+from ...test_pipeline_mixin import PipelineTesterMixin
 
 
 if is_torch_available():
@@ -280,7 +281,7 @@ class MraModelTester:
 
 
 @require_torch
-class MraModelTest(ModelTesterMixin, unittest.TestCase):
+class MraModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase):
     all_model_classes = (
         (
             MraModel,
@@ -299,6 +300,18 @@ class MraModelTest(ModelTesterMixin, unittest.TestCase):
     has_attentions = False
 
     all_generative_model_classes = ()
+    pipeline_model_mapping = (
+        {
+            "feature-extraction": MraModel,
+            "fill-mask": MraForMaskedLM,
+            "question-answering": MraForQuestionAnswering,
+            "text-classification": MraForSequenceClassification,
+            "token-classification": MraForTokenClassification,
+            "zero-shot": MraForSequenceClassification,
+        }
+        if is_torch_available()
+        else {}
+    )
 
     def setUp(self):
         self.model_tester = MraModelTester(self)

tests/models/pvt/test_modeling_pvt.py

@@ -30,6 +30,7 @@ from transformers.testing_utils import (
 
 from ...test_configuration_common import ConfigTester
 from ...test_modeling_common import ModelTesterMixin, floats_tensor, ids_tensor
+from ...test_pipeline_mixin import PipelineTesterMixin
 
 
 if is_torch_available():
@@ -154,8 +155,13 @@ def prepare_img():
 
 
 @require_torch
-class PvtModelTest(ModelTesterMixin, unittest.TestCase):
+class PvtModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase):
     all_model_classes = (PvtModel, PvtForImageClassification) if is_torch_available() else ()
+    pipeline_model_mapping = (
+        {"feature-extraction": PvtModel, "image-classification": PvtForImageClassification}
+        if is_torch_available()
+        else {}
+    )
 
     test_head_masking = False
     test_pruning = False

tests/models/t5/test_modeling_t5.py

@@ -560,11 +560,11 @@ class T5ModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin,
         {
             "conversational": T5ForConditionalGeneration,
             "feature-extraction": T5Model,
+            "question-answering": T5ForQuestionAnswering,
             "summarization": T5ForConditionalGeneration,
+            "text-classification": T5ForSequenceClassification,
             "text2text-generation": T5ForConditionalGeneration,
             "translation": T5ForConditionalGeneration,
-            "question-answering": T5ForQuestionAnswering,
-            "text-classification": T5ForSequenceClassification,
             "zero-shot": T5ForSequenceClassification,
         }
         if is_torch_available()
@@ -583,6 +583,16 @@ class T5ModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin,
         self.model_tester = T5ModelTester(self)
         self.config_tester = ConfigTester(self, config_class=T5Config, d_model=37)
 
+    # `QAPipelineTests` is not working well with slow tokenizers (for some models) and we don't want to touch the file
+    # `src/transformers/data/processors/squad.py` (where this test fails for this model)
+    def is_pipeline_test_to_skip(
+        self, pipeline_test_casse_name, config_class, model_architecture, tokenizer_name, processor_name
+    ):
+        if pipeline_test_casse_name == "QAPipelineTests" and not tokenizer_name.endswith("Fast"):
+            return True
+
+        return False
+
     def _create_and_check_torch_fx_tracing(self, config, inputs_dict, output_loss=False):
         if not is_torch_fx_available() or not self.fx_compatible:
             return

tests/models/umt5/test_modeling_umt5.py

@@ -296,11 +296,11 @@ class UMT5ModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin
         {
             "conversational": UMT5ForConditionalGeneration,
             "feature-extraction": UMT5Model,
+            "question-answering": UMT5ForQuestionAnswering,
             "summarization": UMT5ForConditionalGeneration,
+            "text-classification": UMT5ForSequenceClassification,
             "text2text-generation": UMT5ForConditionalGeneration,
             "translation": UMT5ForConditionalGeneration,
-            "question-answering": UMT5ForQuestionAnswering,
-            "text-classification": UMT5ForSequenceClassification,
             "zero-shot": UMT5ForSequenceClassification,
         }
         if is_torch_available()
@@ -317,6 +317,16 @@ class UMT5ModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin
     def setUp(self):
         self.model_tester = UMT5ModelTester(self)
 
+    # `QAPipelineTests` is not working well with slow tokenizers (for some models) and we don't want to touch the file
+    # `src/transformers/data/processors/squad.py` (where this test fails for this model)
+    def is_pipeline_test_to_skip(
+        self, pipeline_test_casse_name, config_class, model_architecture, tokenizer_name, processor_name
+    ):
+        if pipeline_test_casse_name == "QAPipelineTests" and not tokenizer_name.endswith("Fast"):
+            return True
+
+        return False
+
     def _create_and_check_torch_fx_tracing(self, config, inputs_dict, output_loss=False):
         if not is_torch_fx_available() or not self.fx_compatible:
             return

tests/models/vivit/test_modeling_vivit.py

@@ -29,6 +29,7 @@ from transformers.utils import cached_property, is_torch_available, is_vision_av
 
 from ...test_configuration_common import ConfigTester
 from ...test_modeling_common import ModelTesterMixin, floats_tensor, ids_tensor
+from ...test_pipeline_mixin import PipelineTesterMixin
 
 
 if is_torch_available():
@@ -153,13 +154,18 @@ class VivitModelTester:
 
 
 @require_torch
-class VivitModelTest(ModelTesterMixin, unittest.TestCase):
+class VivitModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase):
     """
     Here we also overwrite some of the tests of test_modeling_common.py, as Vivit does not use input_ids, inputs_embeds,
     attention_mask and seq_length.
     """
 
     all_model_classes = (VivitModel, VivitForVideoClassification) if is_torch_available() else ()
+    pipeline_model_mapping = (
+        {"feature-extraction": VivitModel, "video-classification": VivitForVideoClassification}
+        if is_torch_available()
+        else {}
+    )
 
     test_pruning = False
     test_torchscript = False

tests/utils/tiny_model_summary.json

@@ -1084,6 +1084,16 @@
         ],
         "sha": "1d6ae6c0b60868dffbef0dddeda381c51c6dcba5"
     },
+    "Data2VecAudioForAudioFrameClassification": {
+        "tokenizer_classes": [],
+        "processor_classes": [
+            "Wav2Vec2FeatureExtractor"
+        ],
+        "model_classes": [
+            "Data2VecAudioForAudioFrameClassification"
+        ],
+        "sha": "a64828b27e73fc8dd95aeb315108ca2f6a66b55f"
+    },
     "Data2VecAudioForCTC": {
         "tokenizer_classes": [],
         "processor_classes": [
@@ -1509,6 +1519,26 @@
         ],
         "sha": "d6c75bc51196f0a683afb12de6310fdda13efefd"
     },
+    "Dinov2ForImageClassification": {
+        "tokenizer_classes": [],
+        "processor_classes": [
+            "BitImageProcessor"
+        ],
+        "model_classes": [
+            "Dinov2ForImageClassification"
+        ],
+        "sha": "ae44840966456aae33641df2c8c8a4af5b457b24"
+    },
+    "Dinov2Model": {
+        "tokenizer_classes": [],
+        "processor_classes": [
+            "BitImageProcessor"
+        ],
+        "model_classes": [
+            "Dinov2Model"
+        ],
+        "sha": "6f560b1cc9806bcf84fe0b0c60b5faf9c29be959"
+    },
     "DistilBertForMaskedLM": {
         "tokenizer_classes": [
             "DistilBertTokenizer",
@@ -3931,6 +3961,122 @@
         ],
         "sha": "2f46357659db2d6d54d870e28073deeea1c8cb64"
     },
+    "MptForCausalLM": {
+        "tokenizer_classes": [
+            "GPTNeoXTokenizerFast"
+        ],
+        "processor_classes": [],
+        "model_classes": [
+            "MptForCausalLM"
+        ],
+        "sha": "500c869b956c65f6b1a7b4867727f124c6f5728a"
+    },
+    "MptForQuestionAnswering": {
+        "tokenizer_classes": [
+            "GPTNeoXTokenizerFast"
+        ],
+        "processor_classes": [],
+        "model_classes": [
+            "MptForQuestionAnswering"
+        ],
+        "sha": "6ee46572bf61eb5e7dbbdaf00b73c4d37efc42d9"
+    },
+    "MptForSequenceClassification": {
+        "tokenizer_classes": [
+            "GPTNeoXTokenizerFast"
+        ],
+        "processor_classes": [],
+        "model_classes": [
+            "MptForSequenceClassification"
+        ],
+        "sha": "f0b9153413b5dfceeb96b67d4b0f22c94bbaf64a"
+    },
+    "MptForTokenClassification": {
+        "tokenizer_classes": [
+            "GPTNeoXTokenizerFast"
+        ],
+        "processor_classes": [],
+        "model_classes": [
+            "MptForTokenClassification"
+        ],
+        "sha": "3f7c3ccd67cd0b2aae56d37613429a64ef813246"
+    },
+    "MptModel": {
+        "tokenizer_classes": [
+            "GPTNeoXTokenizerFast"
+        ],
+        "processor_classes": [],
+        "model_classes": [
+            "MptModel"
+        ],
+        "sha": "ea747f234556661b0c8b84a626f267066ce586bf"
+    },
+    "MraForMaskedLM": {
+        "tokenizer_classes": [
+            "RobertaTokenizer",
+            "RobertaTokenizerFast"
+        ],
+        "processor_classes": [],
+        "model_classes": [
+            "MraForMaskedLM"
+        ],
+        "sha": "c00ee46cfd2b8fed29cc37f0a4ead40ad51a439c"
+    },
+    "MraForMultipleChoice": {
+        "tokenizer_classes": [
+            "RobertaTokenizer",
+            "RobertaTokenizerFast"
+        ],
+        "processor_classes": [],
+        "model_classes": [
+            "MraForMultipleChoice"
+        ],
+        "sha": "f397469ba8109f64dab2d75335ea7bf0c2dbeb74"
+    },
+    "MraForQuestionAnswering": {
+        "tokenizer_classes": [
+            "RobertaTokenizer",
+            "RobertaTokenizerFast"
+        ],
+        "processor_classes": [],
+        "model_classes": [
+            "MraForQuestionAnswering"
+        ],
+        "sha": "c2ed75acd20e5440a76d6504d9a3ebc2513011f0"
+    },
+    "MraForSequenceClassification": {
+        "tokenizer_classes": [
+            "RobertaTokenizer",
+            "RobertaTokenizerFast"
+        ],
+        "processor_classes": [],
+        "model_classes": [
+            "MraForSequenceClassification"
+        ],
+        "sha": "f47672d3708508bda7774215bee44a92ec16ab2f"
+    },
+    "MraForTokenClassification": {
+        "tokenizer_classes": [
+            "RobertaTokenizer",
+            "RobertaTokenizerFast"
+        ],
+        "processor_classes": [],
+        "model_classes": [
+            "MraForTokenClassification"
+        ],
+        "sha": "f0961ab5818bca473607fb94b391c186dc1d3492"
+    },
+    "MraModel": {
+        "tokenizer_classes": [
+            "RobertaTokenizer",
+            "RobertaTokenizerFast"
+        ],
+        "processor_classes": [],
+        "model_classes": [
+            "MraModel"
+        ],
+        "sha": "315f34f30bcc4b0b66b11987726df2a80c50e271"
+    },
     "MvpForCausalLM": {
         "tokenizer_classes": [
             "MvpTokenizer",
@@ -4500,7 +4646,8 @@
             "T5TokenizerFast"
         ],
         "processor_classes": [
-            "Pix2StructImageProcessor"
+            "Pix2StructImageProcessor",
+            "Pix2StructProcessor"
         ],
         "model_classes": [],
         "sha": "42b3de00ad535076c4893e4ac5ae2d2748cc4ccb"
@@ -4555,6 +4702,26 @@
         ],
         "sha": "f1ddbbcc768c7ba54c4d75b319540c1635e65937"
     },
+    "PvtForImageClassification": {
+        "tokenizer_classes": [],
+        "processor_classes": [
+            "PvtImageProcessor"
+        ],
+        "model_classes": [
+            "PvtForImageClassification"
+        ],
+        "sha": "589b37bd6941aff6dd248259f9eee3c422a41fde"
+    },
+    "PvtModel": {
+        "tokenizer_classes": [],
+        "processor_classes": [
+            "PvtImageProcessor"
+        ],
+        "model_classes": [
+            "PvtModel"
+        ],
+        "sha": "c40765c382515ae627652d60e9077b6478448d48"
+    },
     "ReformerForMaskedLM": {
         "tokenizer_classes": [
             "ReformerTokenizer",
@@ -5498,6 +5665,18 @@
         ],
         "sha": "275bbf6d389bfd0540b9f824c609c6b22a577328"
     },
+    "T5EncoderModel": {
+        "tokenizer_classes": [
+            "T5Tokenizer",
+            "T5TokenizerFast"
+        ],
+        "processor_classes": [],
+        "model_classes": [
+            "T5EncoderModel",
+            "TFT5EncoderModel"
+        ],
+        "sha": "1c75090036a2b3740dfe2d570b889332ad8e59e8"
+    },
     "T5ForConditionalGeneration": {
         "tokenizer_classes": [
             "T5Tokenizer",
@@ -5510,6 +5689,28 @@
         ],
         "sha": "593fd6072a4e265f5cc73b1973cd8af76b261f29"
     },
+    "T5ForQuestionAnswering": {
+        "tokenizer_classes": [
+            "T5Tokenizer",
+            "T5TokenizerFast"
+        ],
+        "processor_classes": [],
+        "model_classes": [
+            "T5ForQuestionAnswering"
+        ],
+        "sha": "b9edf2de494244ff032f67d2d7bdf6c591000c94"
+    },
+    "T5ForSequenceClassification": {
+        "tokenizer_classes": [
+            "T5Tokenizer",
+            "T5TokenizerFast"
+        ],
+        "processor_classes": [],
+        "model_classes": [
+            "T5ForSequenceClassification"
+        ],
+        "sha": "105b5c4c8e1efe927444108f1388c4f102ebad15"
+    },
     "T5Model": {
         "tokenizer_classes": [
             "T5Tokenizer",
@@ -5659,6 +5860,50 @@
         ],
         "sha": "c3cbf7a6159c038f333ce7adda2480ea3396b2b3"
     },
+    "UMT5EncoderModel": {
+        "tokenizer_classes": [
+            "T5Tokenizer",
+            "T5TokenizerFast"
+        ],
+        "processor_classes": [],
+        "model_classes": [
+            "UMT5EncoderModel"
+        ],
+        "sha": "2894e49c9fbd17ea4b3dab56ec388be354c1a5f0"
+    },
+    "UMT5ForQuestionAnswering": {
+        "tokenizer_classes": [
+            "T5Tokenizer",
+            "T5TokenizerFast"
+        ],
+        "processor_classes": [],
+        "model_classes": [
+            "UMT5ForQuestionAnswering"
+        ],
+        "sha": "b381aa068a44200db539f2f48f4e34a5ed1cb093"
+    },
+    "UMT5ForSequenceClassification": {
+        "tokenizer_classes": [
+            "T5Tokenizer",
+            "T5TokenizerFast"
+        ],
+        "processor_classes": [],
+        "model_classes": [
+            "UMT5ForSequenceClassification"
+        ],
+        "sha": "aa9f77b7b3cff21425b7512e7c0f478af7b5db14"
+    },
+    "UMT5Model": {
+        "tokenizer_classes": [
+            "T5Tokenizer",
+            "T5TokenizerFast"
+        ],
+        "processor_classes": [],
+        "model_classes": [
+            "UMT5Model"
+        ],
+        "sha": "9180d850b24e5494442a4f7a8ca1a4c102f9babd"
+    },
     "UniSpeechForCTC": {
         "tokenizer_classes": [
             "Wav2Vec2CTCTokenizer"
@@ -5707,6 +5952,18 @@
         ],
         "sha": "18e170eb1091715b74ace28c8c380b6bf2b6202d"
     },
+    "UniSpeechSatForAudioFrameClassification": {
+        "tokenizer_classes": [
+            "Wav2Vec2CTCTokenizer"
+        ],
+        "processor_classes": [
+            "Wav2Vec2FeatureExtractor"
+        ],
+        "model_classes": [
+            "UniSpeechSatForAudioFrameClassification"
+        ],
+        "sha": "7eba5a1c6cd610928b27ecb217bb17c729a07a57"
+    },
     "UniSpeechSatForCTC": {
         "tokenizer_classes": [
             "Wav2Vec2CTCTokenizer"
@@ -5997,6 +6254,18 @@
         ],
         "sha": "85020189fb7bf1217eb9370b09bca8ec5bcfdafa"
     },
+    "Wav2Vec2ConformerForAudioFrameClassification": {
+        "tokenizer_classes": [
+            "Wav2Vec2CTCTokenizer"
+        ],
+        "processor_classes": [
+            "Wav2Vec2FeatureExtractor"
+        ],
+        "model_classes": [
+            "Wav2Vec2ConformerForAudioFrameClassification"
+        ],
+        "sha": "e316a18a1d165b4cb51a7f28f8e8dab676da4b56"
+    },
     "Wav2Vec2ConformerForCTC": {
         "tokenizer_classes": [
             "Wav2Vec2CTCTokenizer"
@@ -6057,6 +6326,18 @@
         ],
         "sha": "ef2fe3aa8c23e6f8696e6612061aaddecae49994"
     },
+    "Wav2Vec2ForAudioFrameClassification": {
+        "tokenizer_classes": [
+            "Wav2Vec2CTCTokenizer"
+        ],
+        "processor_classes": [
+            "Wav2Vec2FeatureExtractor"
+        ],
+        "model_classes": [
+            "Wav2Vec2ForAudioFrameClassification"
+        ],
+        "sha": "ab219f119e10f56e1059966c66d23f0df3c2c343"
+    },
     "Wav2Vec2ForCTC": {
         "tokenizer_classes": [
             "Wav2Vec2CTCTokenizer"
@@ -6101,6 +6382,7 @@
             "Wav2Vec2FeatureExtractor"
         ],
         "model_classes": [
+            "TFWav2Vec2ForSequenceClassification",
             "Wav2Vec2ForSequenceClassification"
         ],
         "sha": "2000b2022abcc37100241485f5872126b70164c9"
@@ -6130,6 +6412,18 @@
         ],
         "sha": "7a998ee3ee0619a52828a79c3eed6872fd053f37"
     },
+    "WavLMForAudioFrameClassification": {
+        "tokenizer_classes": [
+            "Wav2Vec2CTCTokenizer"
+        ],
+        "processor_classes": [
+            "Wav2Vec2FeatureExtractor"
+        ],
+        "model_classes": [
+            "WavLMForAudioFrameClassification"
+        ],
+        "sha": "b135610f8d5de0b1a5bf5ed7212966135c63d6ec"
+    },
     "WavLMForCTC": {
         "tokenizer_classes": [
             "Wav2Vec2CTCTokenizer"