Even more TF test fixes (#28146)

* Fix vision text dual encoder

* Small cleanup for wav2vec2 (not fixed yet)

* Small fix for vision_encoder_decoder

* Fix SAM builds

* Update TFBertTokenizer test with modern exporting + tokenizer

* Fix DeBERTa

* Fix DeBERTav2

* Try RAG fix but it's impossible to test locally

* Actually fix RAG now that I got FAISS working somehow

* Fix Wav2Vec2, add sermon

* Fix Hubert

tests/models/bert/test_tokenization_bert_tf.py

@@ -28,7 +28,7 @@ if is_tf_available():
 
         def call(self, inputs):
             tokenized = self.tokenizer(inputs)
-            out = self.bert(**tokenized)
+            out = self.bert(tokenized)
             return out["pooler_output"]
 
 
@@ -41,13 +41,8 @@ class BertTokenizationTest(unittest.TestCase):
     def setUp(self):
         super().setUp()
 
-        self.tokenizers = [
-            BertTokenizer.from_pretrained(checkpoint) for checkpoint in (TOKENIZER_CHECKPOINTS * 2)
-        ]  # repeat for when fast_bert_tokenizer=false
-        self.tf_tokenizers = [TFBertTokenizer.from_pretrained(checkpoint) for checkpoint in TOKENIZER_CHECKPOINTS] + [
-            TFBertTokenizer.from_pretrained(checkpoint, use_fast_bert_tokenizer=False)
-            for checkpoint in TOKENIZER_CHECKPOINTS
-        ]
+        self.tokenizers = [BertTokenizer.from_pretrained(checkpoint) for checkpoint in TOKENIZER_CHECKPOINTS]
+        self.tf_tokenizers = [TFBertTokenizer.from_pretrained(checkpoint) for checkpoint in TOKENIZER_CHECKPOINTS]
         assert len(self.tokenizers) == len(self.tf_tokenizers)
 
         self.test_sentences = [
@@ -94,15 +89,15 @@ class BertTokenizationTest(unittest.TestCase):
                     self.assertTrue(tf.reduce_all(eager_outputs[key] == compiled_outputs[key]))
 
     @slow
-    def test_saved_model(self):
+    def test_export_for_inference(self):
         for tf_tokenizer in self.tf_tokenizers:
             model = ModelToSave(tokenizer=tf_tokenizer)
             test_inputs = tf.convert_to_tensor(self.test_sentences)
             out = model(test_inputs)  # Build model with some sample inputs
             with TemporaryDirectory() as tempdir:
                 save_path = Path(tempdir) / "saved.model"
-                model.save(save_path)
-                loaded_model = tf.keras.models.load_model(save_path)
-            loaded_output = loaded_model(test_inputs)
+                model.export(save_path)
+                loaded_model = tf.saved_model.load(save_path)
+            loaded_output = loaded_model.serve(test_inputs)
             # We may see small differences because the loaded model is compiled, so we need an epsilon for the test
             self.assertLessEqual(tf.reduce_max(tf.abs(out - loaded_output)), 1e-5)

tests/models/rag/test_modeling_tf_rag.py

@@ -1005,6 +1005,7 @@ class TFRagModelSaveLoadTests(unittest.TestCase):
                 retriever=rag_retriever,
                 config=rag_config,
             )
+            rag_sequence.build_in_name_scope()
             # check that the from pretrained methods work
             rag_sequence.save_pretrained(tmp_dirname)
             rag_sequence.from_pretrained(tmp_dirname, retriever=rag_retriever)
@@ -1056,6 +1057,7 @@ class TFRagModelSaveLoadTests(unittest.TestCase):
                 retriever=rag_retriever,
                 config=rag_config,
             )
+            rag_token.build_in_name_scope()
             # check that the from pretrained methods work
             rag_token.save_pretrained(tmp_dirname)
             rag_token.from_pretrained(tmp_dirname, retriever=rag_retriever)

tests/models/vision_encoder_decoder/test_modeling_tf_vision_encoder_decoder.py

@@ -858,6 +858,7 @@ class TFVisionEncoderDecoderModelSaveLoadTests(unittest.TestCase):
                 pretrained_encoder_dir,
                 pretrained_decoder_dir,
             )
+            enc_dec_model.build_in_name_scope()
             # check that the from pretrained methods work
             enc_dec_model.save_pretrained(tmp_dirname)
             enc_dec_model = TFVisionEncoderDecoderModel.from_pretrained(tmp_dirname)