Clean up deprecation warnings (#19654)

* Clean up deprecation warnings

Notes:
Changed some strings in tests to raw strings, which will change the literal content of the strings as they are fed into whatever machine handles them.
Test cases for past in the past/past_key_values switch changed/removed due to warning of impending removal

* Add PILImageResampling abstraction for PIL.Image.Resampling

src/transformers/models/wav2vec2/modeling_flax_wav2vec2.py

@@ -150,7 +150,7 @@ def _compute_mask_indices(
         num_masked_spans = sequence_length // mask_length
 
     # SpecAugment mask to fill
-    spec_aug_mask = np.zeros((batch_size, sequence_length), dtype=np.bool)
+    spec_aug_mask = np.zeros((batch_size, sequence_length), dtype=bool)
 
     # get random indices to mask
     spec_aug_mask_idxs = np.array(

src/transformers/models/wav2vec2/modeling_wav2vec2.py

@@ -193,7 +193,7 @@ def _compute_mask_indices(
     )
 
     # SpecAugment mask to fill
-    spec_aug_mask = np.zeros((batch_size, sequence_length), dtype=np.bool)
+    spec_aug_mask = np.zeros((batch_size, sequence_length), dtype=bool)
     spec_aug_mask_idxs = []
 
     max_num_masked_span = compute_num_masked_span(sequence_length)
@@ -266,7 +266,7 @@ def _sample_negative_indices(
     sampled_negative_indices = np.zeros(shape=(batch_size, sequence_length, num_negatives), dtype=np.int32)
 
     mask_time_indices = (
-        mask_time_indices.astype(np.bool) if mask_time_indices is not None else np.ones(features_shape, dtype=np.bool)
+        mask_time_indices.astype(bool) if mask_time_indices is not None else np.ones(features_shape, dtype=bool)
     )
 
     for batch_idx in range(batch_size):

src/transformers/models/wav2vec2_conformer/modeling_wav2vec2_conformer.py

@@ -190,7 +190,7 @@ def _compute_mask_indices(
     )
 
     # SpecAugment mask to fill
-    spec_aug_mask = np.zeros((batch_size, sequence_length), dtype=np.bool)
+    spec_aug_mask = np.zeros((batch_size, sequence_length), dtype=bool)
     spec_aug_mask_idxs = []
 
     max_num_masked_span = compute_num_masked_span(sequence_length)
@@ -264,7 +264,7 @@ def _sample_negative_indices(
     sampled_negative_indices = np.zeros(shape=(batch_size, sequence_length, num_negatives), dtype=np.int32)
 
     mask_time_indices = (
-        mask_time_indices.astype(np.bool) if mask_time_indices is not None else np.ones(features_shape, dtype=np.bool)
+        mask_time_indices.astype(bool) if mask_time_indices is not None else np.ones(features_shape, dtype=bool)
     )
 
     for batch_idx in range(batch_size):

src/transformers/models/wavlm/modeling_wavlm.py

@@ -142,7 +142,7 @@ def _compute_mask_indices(
     )
 
     # SpecAugment mask to fill
-    spec_aug_mask = np.zeros((batch_size, sequence_length), dtype=np.bool)
+    spec_aug_mask = np.zeros((batch_size, sequence_length), dtype=bool)
     spec_aug_mask_idxs = []
 
     max_num_masked_span = compute_num_masked_span(sequence_length)

src/transformers/models/xglm/modeling_tf_xglm.py

@@ -898,7 +898,7 @@ class TFXGLMForCausalLM(TFXGLMPreTrainedModel, TFCausalLanguageModelingLoss):
         return {
             "input_ids": inputs,
             "attention_mask": attention_mask,
-            "past": past,
+            "past_key_values": past,
             "use_cache": use_cache,
         }
 

tests/models/beit/test_modeling_flax_beit.py

@@ -233,7 +233,7 @@ class FlaxBeitModelIntegrationTest(unittest.TestCase):
         pixel_values = feature_extractor(images=image, return_tensors="np").pixel_values
 
         # prepare bool_masked_pos
-        bool_masked_pos = np.ones((1, 196), dtype=np.bool)
+        bool_masked_pos = np.ones((1, 196), dtype=bool)
 
         # forward pass
         outputs = model(pixel_values=pixel_values, bool_masked_pos=bool_masked_pos)

tests/models/flava/test_feature_extraction_flava.py

@@ -31,6 +31,7 @@ if is_vision_available():
     from PIL import Image
 
     from transformers import FlavaFeatureExtractor
+    from transformers.image_utils import PILImageResampling
     from transformers.models.flava.feature_extraction_flava import (
         FLAVA_CODEBOOK_MEAN,
         FLAVA_CODEBOOK_STD,
@@ -80,7 +81,7 @@ class FlavaFeatureExtractionTester(unittest.TestCase):
         self.min_resolution = min_resolution
         self.max_resolution = max_resolution
         self.size = size
-        self.resample = resample if resample is not None else Image.BICUBIC
+        self.resample = resample if resample is not None else PILImageResampling.BICUBIC
         self.do_normalize = do_normalize
         self.image_mean = image_mean
         self.image_std = image_std
@@ -96,7 +97,7 @@ class FlavaFeatureExtractionTester(unittest.TestCase):
 
         self.codebook_do_resize = codebook_do_resize
         self.codebook_size = codebook_size
-        self.codebook_resample = codebook_resample if codebook_resample is not None else Image.LANCZOS
+        self.codebook_resample = codebook_resample if codebook_resample is not None else PILImageResampling.LANCZOS
         self.codebook_do_center_crop = codebook_do_center_crop
         self.codebook_crop_size = codebook_crop_size
         self.codebook_do_map_pixels = codebook_do_map_pixels

tests/models/wav2vec2/test_modeling_flax_wav2vec2.py

@@ -362,7 +362,7 @@ class FlaxWav2Vec2UtilsTest(unittest.TestCase):
         self.assertTrue(abs(ppl.item() - 141.4291) < 1e-3)
 
         # mask half of the input
-        mask = np.ones((2,), dtype=np.bool)
+        mask = np.ones((2,), dtype=bool)
         mask[0] = 0
 
         ppl = FlaxWav2Vec2GumbelVectorQuantizer._compute_perplexity(probs, mask)

tests/pipelines/test_pipelines_question_answering.py

@@ -93,7 +93,7 @@ class QAPipelineTests(unittest.TestCase, metaclass=PipelineTestCaseMeta):
             question_answerer(question="In what field is HuggingFace working ?", context=None)
 
         outputs = question_answerer(
-            question="Where was HuggingFace founded ?", context="HuggingFace was founded in Paris.", topk=20
+            question="Where was HuggingFace founded ?", context="HuggingFace was founded in Paris.", top_k=20
         )
         self.assertEqual(
             outputs, [{"answer": ANY(str), "start": ANY(int), "end": ANY(int), "score": ANY(float)} for i in range(20)]

tests/test_modeling_tf_common.py

@@ -1984,9 +1984,14 @@ class UtilsFunctionsTest(unittest.TestCase):
 
             @unpack_inputs
             def call(
-                self, input_ids=None, past=None, output_attentions=None, output_hidden_states=None, return_dict=None
+                self,
+                input_ids=None,
+                past_key_values=None,
+                output_attentions=None,
+                output_hidden_states=None,
+                return_dict=None,
             ):
-                return input_ids, past, output_attentions, output_hidden_states, return_dict
+                return input_ids, past_key_values, output_attentions, output_hidden_states, return_dict
 
             @unpack_inputs
             def foo(self, pixel_values, output_attentions=None, output_hidden_states=None, return_dict=None):
@@ -1994,55 +1999,48 @@ class UtilsFunctionsTest(unittest.TestCase):
 
         dummy_model = DummyModel()
         input_ids = tf.constant([0, 1, 2, 3], dtype=tf.int64)
-        past = tf.constant([4, 5, 6, 7], dtype=tf.int64)
+        past_key_values = tf.constant([4, 5, 6, 7], dtype=tf.int64)
         pixel_values = tf.constant([8, 9, 10, 11], dtype=tf.int64)
 
         # test case 1: Pass inputs as keyword arguments; Booleans are inherited from the config.
-        output = dummy_model.call(input_ids=input_ids, past=past)
+        output = dummy_model.call(input_ids=input_ids, past_key_values=past_key_values)
         tf.debugging.assert_equal(output[0], input_ids)
-        tf.debugging.assert_equal(output[1], past)
+        tf.debugging.assert_equal(output[1], past_key_values)
         self.assertFalse(output[2])
         self.assertFalse(output[3])
         self.assertFalse(output[4])
 
         # test case 2: Same as above, but with positional arguments.
-        output = dummy_model.call(input_ids, past)
+        output = dummy_model.call(input_ids, past_key_values)
         tf.debugging.assert_equal(output[0], input_ids)
-        tf.debugging.assert_equal(output[1], past)
+        tf.debugging.assert_equal(output[1], past_key_values)
         self.assertFalse(output[2])
         self.assertFalse(output[3])
         self.assertFalse(output[4])
 
         # test case 3: We can also pack everything in the first input.
-        output = dummy_model.call(input_ids={"input_ids": input_ids, "past": past})
+        output = dummy_model.call(input_ids={"input_ids": input_ids, "past_key_values": past_key_values})
         tf.debugging.assert_equal(output[0], input_ids)
-        tf.debugging.assert_equal(output[1], past)
+        tf.debugging.assert_equal(output[1], past_key_values)
         self.assertFalse(output[2])
         self.assertFalse(output[3])
         self.assertFalse(output[4])
 
         # test case 4: Explicit boolean arguments should override the config.
-        output = dummy_model.call(input_ids=input_ids, past=past, output_attentions=False, return_dict=True)
+        output = dummy_model.call(
+            input_ids=input_ids, past_key_values=past_key_values, output_attentions=False, return_dict=True
+        )
         tf.debugging.assert_equal(output[0], input_ids)
-        tf.debugging.assert_equal(output[1], past)
+        tf.debugging.assert_equal(output[1], past_key_values)
         self.assertFalse(output[2])
         self.assertFalse(output[3])
         self.assertTrue(output[4])
 
         # test case 5: Unexpected arguments should raise an exception.
         with self.assertRaises(ValueError):
-            output = dummy_model.call(input_ids=input_ids, past=past, foo="bar")
-
-        # test case 6: Despite the above, `past_key_values` should be interchangeable with `past`
-        # (the decorator moves it to `past`, or vice-versa, depending on the signature).
-        output = dummy_model.call(input_ids=input_ids, past_key_values=past)
-        tf.debugging.assert_equal(output[0], input_ids)
-        tf.debugging.assert_equal(output[1], past)
-        self.assertFalse(output[2])
-        self.assertFalse(output[3])
-        self.assertFalse(output[4])
+            output = dummy_model.call(input_ids=input_ids, past_key_values=past_key_values, foo="bar")
 
-        # test case 7: the decorator is independent from `main_input_name` -- it treats the first argument of the
+        # test case 6: the decorator is independent from `main_input_name` -- it treats the first argument of the
         # decorated function as its main input.
         output = dummy_model.foo(pixel_values=pixel_values)
         tf.debugging.assert_equal(output[0], pixel_values)