Big TF test cleanup (#24282)

* Fix one BLIP arg not being optional, remove misspelled arg

* Remove the lxmert test overrides and just use the base test_saved_model_creation

* saved_model_creation fixes and re-enabling tests across the board

* Remove unnecessary skip

* Stop caching sinusoidal embeddings in speech_to_text

* Fix transfo_xl compilation

* Fix transfo_xl compilation

* Fix the conditionals in xglm

* Set the save spec only when building

* Clarify comment

* Move comment correctly

* Correct embeddings generation for speech2text

* Mark RAG generation tests as @slow

* Remove redundant else:

* Add comment to clarify the save_spec line in build()

* Fix size tests for XGLM at last!

* make fixup

* Remove one band_part operation

* Mark test_keras_fit as @slow

tests/models/mobilebert/test_modeling_tf_mobilebert.py

@@ -20,7 +20,7 @@ import unittest
 
 from transformers import MobileBertConfig, is_tf_available
 from transformers.models.auto import get_values
-from transformers.testing_utils import require_tf, slow, tooslow
+from transformers.testing_utils import require_tf, slow
 
 from ...test_configuration_common import ConfigTester
 from ...test_modeling_tf_common import TFModelTesterMixin, ids_tensor, random_attention_mask
@@ -311,15 +311,6 @@ class TFMobileBertModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.Te
         config_and_inputs = self.model_tester.prepare_config_and_inputs()
         self.model_tester.create_and_check_mobilebert_for_token_classification(*config_and_inputs)
 
-    @slow
-    def test_keras_fit(self):
-        # Override as it is a slow test on this model
-        super().test_keras_fit()
-
-    @tooslow
-    def test_saved_model_creation(self):
-        pass
-
     @slow
     def test_model_from_pretrained(self):
         # for model_name in TF_MOBILEBERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]:

tests/models/opt/test_modeling_tf_opt.py

@@ -20,7 +20,7 @@ import unittest
 import numpy as np
 
 from transformers import OPTConfig, is_tf_available
-from transformers.testing_utils import require_sentencepiece, require_tf, slow, tooslow
+from transformers.testing_utils import require_sentencepiece, require_tf, slow
 
 from ...test_configuration_common import ConfigTester
 from ...test_modeling_tf_common import TFModelTesterMixin, ids_tensor
@@ -219,10 +219,6 @@ class TFOPTModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.TestCase)
                             models_equal = False
                     self.assertTrue(models_equal)
 
-    @tooslow
-    def test_saved_model_creation(self):
-        pass
-
 
 def _long_tensor(tok_lst):
     return tf.constant(tok_lst, dtype=tf.int32)

tests/models/pegasus/test_modeling_tf_pegasus.py

@@ -18,7 +18,7 @@ from __future__ import annotations
 import unittest
 
 from transformers import AutoTokenizer, PegasusConfig, is_tf_available
-from transformers.testing_utils import require_sentencepiece, require_tf, require_tokenizers, slow, tooslow
+from transformers.testing_utils import require_sentencepiece, require_tf, require_tokenizers, slow
 from transformers.utils import cached_property
 
 from ...test_configuration_common import ConfigTester
@@ -206,10 +206,6 @@ class TFPegasusModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.TestC
         config_and_inputs = self.model_tester.prepare_config_and_inputs_for_common()
         self.model_tester.check_decoder_model_past_large_inputs(*config_and_inputs)
 
-    @tooslow
-    def test_saved_model_creation(self):
-        pass
-
 
 @require_sentencepiece
 @require_tokenizers

tests/models/rag/test_modeling_tf_rag.py

@@ -490,6 +490,7 @@ class TFRagTestMixin:
         inputs_dict = self.config_and_inputs
         self.check_model_without_retriever(**inputs_dict)
 
+    @slow
     def test_model_generate_from_context_input_ids(self):
         inputs_dict = self.config_and_inputs
         self.check_model_generate_from_context_input_ids(**inputs_dict)
@@ -498,6 +499,7 @@ class TFRagTestMixin:
         inputs_dict = self.config_and_inputs
         self.check_model_with_encoder_outputs(**inputs_dict)
 
+    @slow
     def test_model_generate(self):
         inputs_dict = self.config_and_inputs
         self.check_model_generate(**inputs_dict)

tests/models/regnet/test_modeling_tf_regnet.py

@@ -148,6 +148,7 @@ class TFRegNetModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.TestCa
         not is_tf_available() or len(tf.config.list_physical_devices("GPU")) == 0,
         reason="TF does not support backprop for grouped convolutions on CPU.",
     )
+    @slow
     def test_keras_fit(self):
         super().test_keras_fit()
 

tests/models/segformer/test_modeling_tf_segformer.py

@@ -347,6 +347,7 @@ class TFSegformerModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.Tes
         not is_tf_available() or len(tf.config.list_physical_devices("GPU")) == 0,
         reason="TF does not support backprop for grouped convolutions on CPU.",
     )
+    @slow
     def test_keras_fit(self):
         config, _ = self.model_tester.prepare_config_and_inputs_for_common()
 

tests/models/speech_to_text/test_modeling_speech_to_text.py

@@ -722,6 +722,10 @@ class Speech2TextModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTest
 
             self.assertTrue(models_equal)
 
+    def test_pt_tf_model_equivalence(self, allow_missing_keys=True):
+        # Allow missing keys since TF doesn't cache the sinusoidal embeddings in an attribute
+        super().test_pt_tf_model_equivalence(allow_missing_keys=allow_missing_keys)
+
 
 @require_torch
 @require_torchaudio

tests/models/speech_to_text/test_modeling_tf_speech_to_text.py

@@ -558,6 +558,10 @@ class TFSpeech2TextModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.T
             ]
             self.assertListEqual(arg_names[: len(expected_arg_names)], expected_arg_names)
 
+    def test_pt_tf_model_equivalence(self, allow_missing_keys=True):
+        # Allow missing keys since TF doesn't cache the sinusoidal embeddings in an attribute
+        super().test_pt_tf_model_equivalence(allow_missing_keys=allow_missing_keys)
+
 
 @require_tf
 @require_sentencepiece

tests/models/swin/test_modeling_tf_swin.py

@@ -23,7 +23,7 @@ import unittest
 import numpy as np
 
 from transformers import SwinConfig
-from transformers.testing_utils import require_tf, require_vision, slow, to_2tuple, tooslow
+from transformers.testing_utils import require_tf, require_vision, slow, to_2tuple
 from transformers.utils import cached_property, is_tf_available, is_vision_available
 
 from ...test_configuration_common import ConfigTester
@@ -232,10 +232,6 @@ class TFSwinModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.TestCase
     def test_inputs_embeds(self):
         pass
 
-    @tooslow
-    def test_saved_model_creation(self):
-        pass
-
     def test_model_common_attributes(self):
         config, _ = self.model_tester.prepare_config_and_inputs_for_common()
 

tests/models/t5/test_modeling_tf_t5.py

@@ -18,7 +18,7 @@ from __future__ import annotations
 import unittest
 
 from transformers import T5Config, is_tf_available
-from transformers.testing_utils import require_sentencepiece, require_tf, require_tokenizers, slow, tooslow
+from transformers.testing_utils import require_sentencepiece, require_tf, require_tokenizers, slow
 from transformers.utils import cached_property
 
 from ...test_configuration_common import ConfigTester
@@ -300,10 +300,6 @@ class TFT5ModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.TestCase):
 
         self.model_tester.create_and_check_t5_decoder_model_past_large_inputs(*config_and_inputs)
 
-    @tooslow
-    def test_saved_model_creation(self):
-        pass
-
     @slow
     def test_model_from_pretrained(self):
         model = TFT5Model.from_pretrained("t5-small")

tests/test_modeling_tf_common.py

@@ -1415,6 +1415,7 @@ class TFModelTesterMixin:
     def check_keras_fit_results(self, val_loss1, val_loss2, atol=1e-2, rtol=1e-3):
         self.assertTrue(np.allclose(val_loss1, val_loss2, atol=atol, rtol=rtol))
 
+    @slow
     def test_keras_fit(self):
         config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common()
         for model_class in self.all_model_classes: