[No merge] TF integration testing (#7621)

* stash

* TF Integration testing for ELECTRA, BERT, Longformer

* Trigger slow tests

* Apply suggestions from code review

src/transformers/modeling_electra.py

@@ -514,7 +514,7 @@ class ElectraDiscriminatorPredictions(nn.Module):
     def forward(self, discriminator_hidden_states):
         hidden_states = self.dense(discriminator_hidden_states)
         hidden_states = get_activation(self.config.hidden_act)(hidden_states)
-        logits = self.dense_prediction(hidden_states).squeeze()
+        logits = self.dense_prediction(hidden_states).squeeze(-1)
 
         return logits
 

src/transformers/modeling_tf_electra.py

@@ -425,7 +425,7 @@ class TFElectraDiscriminatorPredictions(tf.keras.layers.Layer):
     def call(self, discriminator_hidden_states, training=False):
         hidden_states = self.dense(discriminator_hidden_states)
         hidden_states = get_tf_activation(self.config.hidden_act)(hidden_states)
-        logits = tf.squeeze(self.dense_prediction(hidden_states))
+        logits = tf.squeeze(self.dense_prediction(hidden_states), -1)
 
         return logits
 

tests/test_modeling_tf_bert.py

@@ -17,7 +17,7 @@
 import unittest
 
 from transformers import BertConfig, is_tf_available
-from transformers.testing_utils import require_tf
+from transformers.testing_utils import require_tf, slow
 
 from .test_configuration_common import ConfigTester
 from .test_modeling_tf_common import TFModelTesterMixin, ids_tensor
@@ -328,3 +328,27 @@ class TFBertModelTest(TFModelTesterMixin, unittest.TestCase):
         self.assertEqual(sorted(output_loading_info["unexpected_keys"]), ["mlm___cls", "nsp___cls"])
         for layer in output_loading_info["missing_keys"]:
             self.assertTrue(layer.split("_")[0] in ["dropout", "classifier"])
+
+
+class TFBertModelIntegrationTest(unittest.TestCase):
+    @slow
+    def test_inference_masked_lm(self):
+        model = TFBertForPreTraining.from_pretrained("lysandre/tiny-bert-random")
+        input_ids = tf.constant([[0, 1, 2, 3, 4, 5]])
+        output = model(input_ids)[0]
+
+        expected_shape = [1, 6, 10]
+        self.assertEqual(output.shape, expected_shape)
+
+        print(output[:, :3, :3])
+
+        expected_slice = tf.constant(
+            [
+                [
+                    [0.03706957, 0.10124919, 0.03616843],
+                    [-0.06099961, 0.02266058, 0.00601412],
+                    [-0.06066202, 0.05684517, 0.02038802],
+                ]
+            ]
+        )
+        tf.debugging.assert_near(output[:, :3, :3], expected_slice, atol=1e-4)

tests/test_modeling_tf_electra.py

@@ -248,3 +248,19 @@ class TFElectraModelTest(TFModelTesterMixin, unittest.TestCase):
         for model_name in ["google/electra-small-discriminator"]:
             model = TFElectraModel.from_pretrained(model_name)
             self.assertIsNotNone(model)
+
+
+class TFElectraModelIntegrationTest(unittest.TestCase):
+    @slow
+    def test_inference_masked_lm(self):
+        model = TFElectraForPreTraining.from_pretrained("lysandre/tiny-electra-random")
+        input_ids = tf.constant([[0, 1, 2, 3, 4, 5]])
+        output = model(input_ids)[0]
+
+        expected_shape = [1, 6]
+        self.assertEqual(output.shape, expected_shape)
+
+        print(output[:, :3])
+
+        expected_slice = tf.constant([[-0.24651965, 0.8835437, 1.823782]])
+        tf.debugging.assert_near(output[:, :3], expected_slice, atol=1e-4)

tests/test_modeling_tf_longformer.py

@@ -622,3 +622,25 @@ class TFLongformerModelIntegrationTest(unittest.TestCase):
         tf.debugging.assert_near(tf.reduce_mean(loss), expected_loss, rtol=1e-4)
         tf.debugging.assert_near(tf.reduce_sum(prediction_scores), expected_prediction_scores_sum, rtol=1e-4)
         tf.debugging.assert_near(tf.reduce_mean(prediction_scores), expected_prediction_scores_mean, rtol=1e-4)
+
+    @slow
+    def test_inference_masked_lm(self):
+        model = TFLongformerForMaskedLM.from_pretrained("lysandre/tiny-longformer-random")
+        input_ids = tf.constant([[0, 1, 2, 3, 4, 5]])
+        output = model(input_ids)[0]
+
+        expected_shape = [1, 6, 10]
+        self.assertEqual(output.shape, expected_shape)
+
+        print(output[:, :3, :3])
+
+        expected_slice = tf.constant(
+            [
+                [
+                    [-0.04926379, 0.0367098, 0.02099686],
+                    [0.03940692, 0.01547744, -0.01448723],
+                    [0.03495252, -0.05900355, -0.01675752],
+                ]
+            ]
+        )
+        tf.debugging.assert_near(output[:, :3, :3], expected_slice, atol=1e-4)