[`Styling`] stylify using ruff (#27144)

* try to stylify using ruff

* might need to remove these changes?

* use ruf format andruff check

* use isinstance instead of type comparision

* use # fmt: skip

* use # fmt: skip

* nits

* soem styling changes

* update ci job

* nits isinstance

* more files update

* nits

* more nits

* small nits

* check and format

* revert wrong changes

* actually use formatter instead of checker

* nits

* well docbuilder is overwriting this commit

* revert notebook changes

* try to nuke docbuilder

* style

* fix feature exrtaction test

* remve `indent-width = 4`

* fixup

* more nits

* update the ruff version that we use

* style

* nuke docbuilder styling

* leve the print for detected changes

* nits

* Remove file I/O
Co-authored-by: charliermarsh <charlie.r.marsh@gmail.com>

* style

* nits

* revert notebook changes

* Add # fmt skip when possible

* Add # fmt skip when possible

* Fix

* More `  # fmt: skip` usage

* More `  # fmt: skip` usage

* More `  # fmt: skip` usage

* NIts

* more fixes

* fix tapas

* Another way to skip

* Recommended way

* Fix two more fiels

* Remove asynch
Remove asynch

---------
Co-authored-by: charliermarsh <charlie.r.marsh@gmail.com>

tests/models/perceiver/test_tokenization_perceiver.py

@@ -113,9 +113,7 @@ class PerceiverTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
     def test_prepare_batch_integration(self):
         tokenizer = self.perceiver_tokenizer
         src_text = ["A long paragraph for summarization.", "Another paragraph for summarization."]
-        # fmt: off
-        expected_src_tokens = [4, 71, 38, 114, 117, 116, 109, 38, 118, 103, 120, 103, 109, 120, 103, 118, 110, 38, 108, 117, 120, 38, 121, 123, 115, 115, 103, 120, 111, 128, 103, 122, 111, 117, 116, 52, 5, 0]
-        # fmt: on
+        expected_src_tokens = [4, 71, 38, 114, 117, 116, 109, 38, 118, 103, 120, 103, 109, 120, 103, 118, 110, 38, 108, 117, 120, 38, 121, 123, 115, 115, 103, 120, 111, 128, 103, 122, 111, 117, 116, 52, 5, 0]  # fmt: skip
         batch = tokenizer(src_text, padding=True, return_tensors=FRAMEWORK)
         self.assertIsInstance(batch, BatchEncoding)
 

tests/models/phi/test_modeling_phi.py

@@ -361,9 +361,7 @@ class PhiIntegrationTest(unittest.TestCase):
 
         output = model(**input_ids).logits
 
-        # fmt: off
-        EXPECTED_OUTPUT = torch.tensor([[2.2671,  6.7684, -2.0107, -1.2440, -1.5335, -2.3828,  6.9186,  6.4245, 3.1548,  0.9998,  0.0760,  4.4653,  4.9857,  4.2956,  1.2308, -1.4178, 0.1361,  0.5191, -0.5699, -2.2201, -3.0750, -3.9600, -4.5936, -3.7394, -2.7777,  6.1874, -0.4148, -1.5684, -0.5967,  0.2395], [1.7004,  4.0383,  0.0546,  0.4530, -0.3619, -0.9021,  1.8355,  1.3587, 1.2406,  2.5775, -0.8834,  5.1910,  4.2565,  4.1406,  3.0752, -0.9099, 1.1595,  0.0264,  0.3243, -1.1803, -1.3945, -2.1406, -3.9939, -1.4438, -2.9546,  3.9204,  1.0851, -1.0598, -1.7819, -0.4827]]).to(torch_device)
-        # fmt: on
+        EXPECTED_OUTPUT = torch.tensor([[2.2671,  6.7684, -2.0107, -1.2440, -1.5335, -2.3828,  6.9186,  6.4245, 3.1548,  0.9998,  0.0760,  4.4653,  4.9857,  4.2956,  1.2308, -1.4178, 0.1361,  0.5191, -0.5699, -2.2201, -3.0750, -3.9600, -4.5936, -3.7394, -2.7777,  6.1874, -0.4148, -1.5684, -0.5967,  0.2395], [1.7004,  4.0383,  0.0546,  0.4530, -0.3619, -0.9021,  1.8355,  1.3587, 1.2406,  2.5775, -0.8834,  5.1910,  4.2565,  4.1406,  3.0752, -0.9099, 1.1595,  0.0264,  0.3243, -1.1803, -1.3945, -2.1406, -3.9939, -1.4438, -2.9546,  3.9204,  1.0851, -1.0598, -1.7819, -0.4827]]).to(torch_device)  # fmt: skip
 
         self.assertTrue(torch.allclose(EXPECTED_OUTPUT, output[0, :2, :30], atol=1e-4, rtol=1e-4))
 
@@ -379,8 +377,6 @@ class PhiIntegrationTest(unittest.TestCase):
 
         output = model(**input_ids).logits
 
-        # fmt: off
-        EXPECTED_OUTPUT = torch.tensor([[12.2922, 13.3507,  8.6963,  9.1355,  9.3502,  9.2667, 14.2027, 13.1363, 13.5446, 11.1337,  9.9279, 16.7195, 13.0768, 14.9141, 11.9965,  8.0233, 10.3129, 10.6118, 10.0204,  9.3827,  8.8344,  8.2806,  8.0153,  8.0540, 7.0964, 16.5743, 11.1256,  9.6987, 11.4770, 10.5440], [12.3323, 14.6050,  8.9986,  8.1580,  9.5654,  6.6728, 12.5966, 12.6662, 12.2784, 11.7522,  8.2039, 16.3102, 11.2203, 13.6088, 12.0125,  9.1021, 9.8216, 10.0987,  9.0926,  8.4260,  8.8009,  7.6547,  6.8075,  7.7881, 7.4501, 15.7451, 10.5053,  8.3129, 10.0027,  9.2612]]).to(torch_device)
-        # fmt: on
+        EXPECTED_OUTPUT = torch.tensor([[12.2922, 13.3507,  8.6963,  9.1355,  9.3502,  9.2667, 14.2027, 13.1363, 13.5446, 11.1337,  9.9279, 16.7195, 13.0768, 14.9141, 11.9965,  8.0233, 10.3129, 10.6118, 10.0204,  9.3827,  8.8344,  8.2806,  8.0153,  8.0540, 7.0964, 16.5743, 11.1256,  9.6987, 11.4770, 10.5440], [12.3323, 14.6050,  8.9986,  8.1580,  9.5654,  6.6728, 12.5966, 12.6662, 12.2784, 11.7522,  8.2039, 16.3102, 11.2203, 13.6088, 12.0125,  9.1021, 9.8216, 10.0987,  9.0926,  8.4260,  8.8009,  7.6547,  6.8075,  7.7881, 7.4501, 15.7451, 10.5053,  8.3129, 10.0027,  9.2612]]).to(torch_device)  # fmt: skip
 
         self.assertTrue(torch.allclose(EXPECTED_OUTPUT, output[0, :2, :30], atol=1e-4, rtol=1e-4))

tests/models/reformer/test_tokenization_reformer.py

@@ -351,9 +351,7 @@ class ReformerTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
 
     @slow
     def test_tokenizer_integration(self):
-        # fmt: off
-        expected_encoding = {'input_ids': [[108, 265, 24, 111, 4, 258, 156, 7, 51, 279, 58, 7, 76, 25, 69, 278], [140, 243, 264, 134, 17, 267, 77, 263, 22, 262, 297, 258, 304, 177, 279, 266, 14, 89, 13, 35, 261, 299, 272, 137, 275, 278]], 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]]}  # noqa: E501
-        # fmt: on
+        expected_encoding = {'input_ids': [[108, 265, 24, 111, 4, 258, 156, 7, 51, 279, 58, 7, 76, 25, 69, 278], [140, 243, 264, 134, 17, 267, 77, 263, 22, 262, 297, 258, 304, 177, 279, 266, 14, 89, 13, 35, 261, 299, 272, 137, 275, 278]], 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]]}  # fmt: skip
 
         # This tokenizer does not know some characters like ")".
         # That is the reason why we use very simple texts here.

tests/models/roberta_prelayernorm/test_modeling_roberta_prelayernorm.py

@@ -493,8 +493,8 @@ class RobertaPreLayerNormModelTest(ModelTesterMixin, GenerationTesterMixin, Pipe
         """Ensure that the default position ids only assign a sequential . This is a regression
         test for https://github.com/huggingface/transformers/issues/1761
 
-        The position ids should be masked with the embedding object's padding index. Therefore, the first available
-        non-padding position index is RobertaPreLayerNormEmbeddings.padding_idx + 1
+        The position ids should be masked with the embedding object's padding index. Therefore, the
+        first available non-padding position index is RobertaPreLayerNormEmbeddings.padding_idx + 1
         """
         config = self.model_tester.prepare_config_and_inputs()[0]
         model = RobertaPreLayerNormEmbeddings(config=config)
@@ -513,8 +513,8 @@ class RobertaPreLayerNormModelTest(ModelTesterMixin, GenerationTesterMixin, Pipe
         """Ensure that the default position ids only assign a sequential . This is a regression
         test for https://github.com/huggingface/transformers/issues/1761
 
-        The position ids should be masked with the embedding object's padding index. Therefore, the first available
-        non-padding position index is RobertaPreLayerNormEmbeddings.padding_idx + 1
+        The position ids should be masked with the embedding object's padding index. Therefore, the
+        first available non-padding position index is RobertaPreLayerNormEmbeddings.padding_idx + 1
         """
         config = self.model_tester.prepare_config_and_inputs()[0]
         embeddings = RobertaPreLayerNormEmbeddings(config=config)

tests/models/sam/test_modeling_sam.py

@@ -728,9 +728,7 @@ class SamModelIntegrationTest(unittest.TestCase):
 
         raw_image = prepare_image()
 
-        # fmt: off
-        input_points = torch.Tensor([[[400, 650]], [[220, 470]]]).cpu()
-        # fmt: on
+        input_points = torch.Tensor([[[400, 650]], [[220, 470]]]).cpu()  # fmt: skip
 
         input_points = input_points.unsqueeze(0)
 

tests/models/sam/test_modeling_tf_sam.py

@@ -628,9 +628,7 @@ class TFSamModelIntegrationTest(unittest.TestCase):
 
         raw_image = prepare_image()
 
-        # fmt: off
-        input_points = tf.convert_to_tensor([[[400, 650]], [[220, 470]]])
-        # fmt: on
+        input_points = tf.convert_to_tensor([[[400, 650]], [[220, 470]]])  # fmt: skip
 
         input_points = tf.expand_dims(input_points, 0)
 

tests/models/seamless_m4t/test_modeling_seamless_m4t.py

@@ -1001,9 +1001,7 @@ class SeamlessM4TModelIntegrationTest(unittest.TestCase):
     def input_text(self):
         # corresponds to "C'est un test." with seamlessM4T_medium checkpoint
 
-        # fmt: off
-        input_ids = torch.tensor([[256057, 152, 248116, 354, 159, 7356, 248075, 3]])
-        # fmt: on
+        input_ids = torch.tensor([[256057, 152, 248116, 354, 159, 7356, 248075, 3]])  # fmt: skip
 
         input_ids = input_ids.to(torch_device)
 
@@ -1049,9 +1047,7 @@ class SeamlessM4TModelIntegrationTest(unittest.TestCase):
 
         # test text - tgt lang: eng
 
-        # fmt: off
-        expected_text_tokens = [3, 256047, 3291, 248116, 248066, 9, 7356, 248075, 3]
-        # fmt: on
+        expected_text_tokens = [3, 256047, 3291, 248116, 248066, 9, 7356, 248075, 3]  # fmt: skip
 
         # fmt: off
         expected_unit_tokens = [
@@ -1062,9 +1058,7 @@ class SeamlessM4TModelIntegrationTest(unittest.TestCase):
         ]
         # fmt: on
 
-        # fmt: off
-        expected_wav_slice = [-3e-05, -0.0004, -0.00037, -0.00013, -6e-05, 0.00012, -0.00016, 0.00025, 7e-05, -3e-05]
-        # fmt: on
+        expected_wav_slice = [-3e-05, -0.0004, -0.00037, -0.00013, -6e-05, 0.00012, -0.00016, 0.00025, 7e-05, -3e-05]  # fmt: skip
 
         set_seed(0)
         output = model.generate(**self.input_text, num_beams=1, tgt_lang="eng", return_intermediate_token_ids=True)
@@ -1081,9 +1075,7 @@ class SeamlessM4TModelIntegrationTest(unittest.TestCase):
 
         # test text - tgt lang: swh
 
-        # fmt: off
-        expected_text_tokens = [3, 256168, 1665, 188589, 7040, 248075, 3]
-        # fmt: on
+        expected_text_tokens = [3, 256168, 1665, 188589, 7040, 248075, 3]  # fmt: skip
 
         # fmt: off
         expected_unit_tokens = [
@@ -1093,9 +1085,7 @@ class SeamlessM4TModelIntegrationTest(unittest.TestCase):
         ]
         # fmt: on
 
-        # fmt: off
-        expected_wav_slice = [1e-05, -7e-05, -4e-05, -4e-05, -6e-05, -9e-05, -0.0001, -2e-05, -7e-05, -2e-05]
-        # fmt: on
+        expected_wav_slice = [1e-05, -7e-05, -4e-05, -4e-05, -6e-05, -9e-05, -0.0001, -2e-05, -7e-05, -2e-05]  # fmt: skip
 
         set_seed(0)
         output = model.generate(**self.input_text, num_beams=1, tgt_lang="swh", return_intermediate_token_ids=True)
@@ -1111,9 +1101,7 @@ class SeamlessM4TModelIntegrationTest(unittest.TestCase):
 
         # test audio - tgt lang: rus
 
-        # fmt: off
-        expected_text_tokens = [3, 256147, 1197, 73565, 3413, 537, 233331, 248075, 3]
-        # fmt: on
+        expected_text_tokens = [3, 256147, 1197, 73565, 3413, 537, 233331, 248075, 3]  # fmt: skip
 
         # fmt: off
         expected_unit_tokens = [
@@ -1124,9 +1112,7 @@ class SeamlessM4TModelIntegrationTest(unittest.TestCase):
         ]
         # fmt: on
 
-        # fmt: off
-        expected_wav_slice = [0.00013, 0.00012, 0.00014, 3e-05, 0.0, -6e-05, -0.00018, -0.00016, -0.00021, -0.00018]
-        # fmt: on
+        expected_wav_slice = [0.00013, 0.00012, 0.00014, 3e-05, 0.0, -6e-05, -0.00018, -0.00016, -0.00021, -0.00018]  # fmt: skip
 
         set_seed(0)
         output = model.generate(**self.input_audio, num_beams=1, tgt_lang="rus", return_intermediate_token_ids=True)

tests/models/seamless_m4t/test_tokenization_seamless_m4t.py

@@ -449,9 +449,7 @@ class SeamlessM4TDistilledIntegrationTest(unittest.TestCase):
         " face decât să înrăutăţească violenţele şi mizeria pentru milioane de oameni.",
     ]
 
-    # fmt: off
-    expected_src_tokens = [256047, 16297, 134408, 8165, 248066, 14734, 950, 1135, 105721, 3573, 83, 27352, 108, 49486, 3]
-    # fmt: on
+    expected_src_tokens = [256047, 16297, 134408, 8165, 248066, 14734, 950, 1135, 105721, 3573, 83, 27352, 108, 49486, 3]  # fmt: skip
 
     @classmethod
     def setUpClass(cls):
@@ -483,9 +481,7 @@ class SeamlessM4TDistilledIntegrationTest(unittest.TestCase):
     # Copied from tests.models.nllb.test_tokenization_nllb.NllbDistilledIntegrationTest.test_enro_tokenizer_decode_ignores_language_codes
     def test_enro_tokenizer_decode_ignores_language_codes(self):
         self.assertIn(RO_CODE, self.tokenizer.all_special_ids)
-        # fmt: off
-        generated_ids = [RO_CODE, 4254, 98068, 112923, 39072, 3909, 713, 102767, 26, 17314, 35642, 14683, 33118, 2022, 66987, 2, 256047]
-        # fmt: on
+        generated_ids = [RO_CODE, 4254, 98068, 112923, 39072, 3909, 713, 102767, 26, 17314, 35642, 14683, 33118, 2022, 66987, 2, 256047]  # fmt: skip
 
         result = self.tokenizer.decode(generated_ids, skip_special_tokens=True)
         expected_romanian = self.tokenizer.decode(generated_ids[1:], skip_special_tokens=True)

tests/models/speech_to_text/test_tokenization_speech_to_text.py

@@ -90,28 +90,16 @@ class SpeechToTextTokenizerTest(TokenizerTesterMixin, unittest.TestCase):
         )
 
         tokens = tokenizer.tokenize("I was born in 92000, and this is falsé.")
-        self.assertListEqual(
-            tokens,
-            # fmt: off
-            [SPIECE_UNDERLINE + "I", SPIECE_UNDERLINE + "was", SPIECE_UNDERLINE + "b", "or", "n", SPIECE_UNDERLINE + "in", SPIECE_UNDERLINE + "", "9", "2", "0", "0", "0", ",", SPIECE_UNDERLINE + "and", SPIECE_UNDERLINE + "this", SPIECE_UNDERLINE + "is", SPIECE_UNDERLINE + "f", "al", "s", "é", "."],
-            # fmt: on
-        )
+        self.assertListEqual(tokens,[SPIECE_UNDERLINE + "I", SPIECE_UNDERLINE + "was", SPIECE_UNDERLINE + "b", "or", "n", SPIECE_UNDERLINE + "in", SPIECE_UNDERLINE + "", "9", "2", "0", "0", "0", ",", SPIECE_UNDERLINE + "and", SPIECE_UNDERLINE + "this", SPIECE_UNDERLINE + "is", SPIECE_UNDERLINE + "f", "al", "s", "é", "."])  # fmt: skip
         ids = tokenizer.convert_tokens_to_ids(tokens)
         self.assertListEqual(ids, [12, 25, 88, 59, 28, 23, 11, 4, 606, 351, 351, 351, 7, 16, 70, 50, 76, 84, 10, 4, 8])
 
         back_tokens = tokenizer.convert_ids_to_tokens(ids)
-        self.assertListEqual(
-            back_tokens,
-            # fmt: off
-            [SPIECE_UNDERLINE + "I", SPIECE_UNDERLINE + "was", SPIECE_UNDERLINE + "b", "or", "n", SPIECE_UNDERLINE + "in", SPIECE_UNDERLINE + "", "<unk>", "2", "0", "0", "0", ",", SPIECE_UNDERLINE + "and", SPIECE_UNDERLINE + "this", SPIECE_UNDERLINE + "is", SPIECE_UNDERLINE + "f", "al", "s", "<unk>", "."],
-            # fmt: on
-        )
+        self.assertListEqual(back_tokens,[SPIECE_UNDERLINE + "I", SPIECE_UNDERLINE + "was", SPIECE_UNDERLINE + "b", "or", "n", SPIECE_UNDERLINE + "in", SPIECE_UNDERLINE + "", "<unk>", "2", "0", "0", "0", ",", SPIECE_UNDERLINE + "and", SPIECE_UNDERLINE + "this", SPIECE_UNDERLINE + "is", SPIECE_UNDERLINE + "f", "al", "s", "<unk>", "."])  # fmt: skip
 
     @slow
     def test_tokenizer_integration(self):
-        # fmt: off
-        expected_encoding = {'input_ids': [[3791, 797, 31, 11, 64, 797, 31, 2429, 433, 12, 1176, 12, 20, 786, 915, 142, 2413, 240, 37, 3238, 797, 31, 11, 35, 93, 915, 142, 2413, 240, 37, 5540, 567, 1276, 93, 37, 610, 40, 62, 455, 657, 1042, 123, 780, 177, 37, 309, 241, 1298, 514, 20, 292, 2737, 114, 2469, 241, 85, 64, 302, 548, 528, 423, 4, 509, 406, 423, 37, 601, 4, 777, 302, 548, 528, 423, 284, 4, 3388, 511, 459, 4, 3555, 40, 321, 302, 705, 4, 3388, 511, 583, 326, 5, 5, 5, 62, 3310, 560, 177, 2680, 217, 1508, 32, 31, 853, 418, 64, 583, 511, 1605, 62, 35, 93, 560, 177, 2680, 217, 1508, 1521, 64, 583, 511, 519, 62, 20, 1515, 764, 20, 149, 261, 5625, 7972, 20, 5540, 567, 1276, 93, 3925, 1675, 11, 15, 802, 7972, 576, 217, 1508, 11, 35, 93, 1253, 2441, 15, 289, 652, 31, 416, 321, 3842, 115, 40, 911, 8, 476, 619, 4, 380, 142, 423, 335, 240, 35, 93, 264, 8, 11, 335, 569, 420, 163, 5, 2], [260, 548, 528, 423, 20, 451, 20, 2681, 1153, 3434, 20, 5540, 37, 567, 126, 1253, 2441, 3376, 449, 210, 431, 1563, 177, 767, 5540, 11, 1203, 472, 11, 2953, 685, 285, 364, 706, 1153, 20, 6799, 20, 2869, 20, 4464, 126, 40, 2429, 20, 1040, 866, 2664, 418, 20, 318, 20, 1726, 186, 20, 265, 522, 35, 93, 2191, 4634, 20, 1040, 12, 6799, 15, 228, 2356, 142, 31, 11, 5, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [2575, 2666, 684, 1582, 1176, 12, 627, 149, 619, 20, 4902, 563, 11, 20, 149, 261, 3420, 2356, 174, 142, 4714, 131, 5, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]], 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]]}  # noqa: E501
-        # fmt: on
+        expected_encoding = {'input_ids': [[3791, 797, 31, 11, 64, 797, 31, 2429, 433, 12, 1176, 12, 20, 786, 915, 142, 2413, 240, 37, 3238, 797, 31, 11, 35, 93, 915, 142, 2413, 240, 37, 5540, 567, 1276, 93, 37, 610, 40, 62, 455, 657, 1042, 123, 780, 177, 37, 309, 241, 1298, 514, 20, 292, 2737, 114, 2469, 241, 85, 64, 302, 548, 528, 423, 4, 509, 406, 423, 37, 601, 4, 777, 302, 548, 528, 423, 284, 4, 3388, 511, 459, 4, 3555, 40, 321, 302, 705, 4, 3388, 511, 583, 326, 5, 5, 5, 62, 3310, 560, 177, 2680, 217, 1508, 32, 31, 853, 418, 64, 583, 511, 1605, 62, 35, 93, 560, 177, 2680, 217, 1508, 1521, 64, 583, 511, 519, 62, 20, 1515, 764, 20, 149, 261, 5625, 7972, 20, 5540, 567, 1276, 93, 3925, 1675, 11, 15, 802, 7972, 576, 217, 1508, 11, 35, 93, 1253, 2441, 15, 289, 652, 31, 416, 321, 3842, 115, 40, 911, 8, 476, 619, 4, 380, 142, 423, 335, 240, 35, 93, 264, 8, 11, 335, 569, 420, 163, 5, 2], [260, 548, 528, 423, 20, 451, 20, 2681, 1153, 3434, 20, 5540, 37, 567, 126, 1253, 2441, 3376, 449, 210, 431, 1563, 177, 767, 5540, 11, 1203, 472, 11, 2953, 685, 285, 364, 706, 1153, 20, 6799, 20, 2869, 20, 4464, 126, 40, 2429, 20, 1040, 866, 2664, 418, 20, 318, 20, 1726, 186, 20, 265, 522, 35, 93, 2191, 4634, 20, 1040, 12, 6799, 15, 228, 2356, 142, 31, 11, 5, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [2575, 2666, 684, 1582, 1176, 12, 627, 149, 619, 20, 4902, 563, 11, 20, 149, 261, 3420, 2356, 174, 142, 4714, 131, 5, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]], 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]]}  # fmt: skip
 
         self.tokenizer_integration_test_util(
             expected_encoding=expected_encoding,

tests/models/speecht5/test_tokenization_speecht5.py

@@ -152,9 +152,7 @@ class SpeechT5TokenizerTest(TokenizerTesterMixin, unittest.TestCase):
         tokenizer = self.get_tokenizer(normalize=True)
 
         tokens = tokenizer.tokenize("This is a test")
-        # fmt: off
-        self.assertListEqual(tokens, [SPIECE_UNDERLINE, 'T', 'h', 'i', 's', SPIECE_UNDERLINE, 'i', 's', SPIECE_UNDERLINE, 'a', SPIECE_UNDERLINE, 't', 'e', 's', 't'])
-        # fmt: on
+        self.assertListEqual(tokens, [SPIECE_UNDERLINE, 'T', 'h', 'i', 's', SPIECE_UNDERLINE, 'i', 's', SPIECE_UNDERLINE, 'a', SPIECE_UNDERLINE, 't', 'e', 's', 't'])  # fmt: skip
 
         self.assertListEqual(
             tokenizer.convert_tokens_to_ids(tokens),
@@ -162,25 +160,13 @@ class SpeechT5TokenizerTest(TokenizerTesterMixin, unittest.TestCase):
         )
 
         tokens = tokenizer.tokenize("I was born in 92000, and this is falsé.")
-        self.assertListEqual(
-            tokens,
-            # fmt: off
-            [SPIECE_UNDERLINE, 'I', SPIECE_UNDERLINE, 'w', 'a', 's', SPIECE_UNDERLINE, 'b', 'o', 'r', 'n', SPIECE_UNDERLINE, 'i', 'n', SPIECE_UNDERLINE, 'n', 'i', 'n', 'e', 't', 'y', SPIECE_UNDERLINE, 't', 'w', 'o', SPIECE_UNDERLINE, 't', 'h', 'o', 'u', 's', 'a', 'n', 'd', ',', SPIECE_UNDERLINE, 'a', 'n', 'd', SPIECE_UNDERLINE, 't', 'h', 'i', 's', SPIECE_UNDERLINE, 'i', 's', SPIECE_UNDERLINE, 'f', 'a', 'l', 's', 'é', '.']
-            # fmt: on
-        )
+        self.assertListEqual(tokens,[SPIECE_UNDERLINE, 'I', SPIECE_UNDERLINE, 'w', 'a', 's', SPIECE_UNDERLINE, 'b', 'o', 'r', 'n', SPIECE_UNDERLINE, 'i', 'n', SPIECE_UNDERLINE, 'n', 'i', 'n', 'e', 't', 'y', SPIECE_UNDERLINE, 't', 'w', 'o', SPIECE_UNDERLINE, 't', 'h', 'o', 'u', 's', 'a', 'n', 'd', ',', SPIECE_UNDERLINE, 'a', 'n', 'd', SPIECE_UNDERLINE, 't', 'h', 'i', 's', SPIECE_UNDERLINE, 'i', 's', SPIECE_UNDERLINE, 'f', 'a', 'l', 's', 'é', '.'])  # fmt: skip
 
         ids = tokenizer.convert_tokens_to_ids(tokens)
-        # fmt: off
-        self.assertListEqual(ids, [4, 30, 4, 20, 7, 12, 4, 25, 8, 13, 9, 4, 10, 9, 4, 9, 10, 9, 5, 6, 22, 4, 6, 20, 8, 4, 6, 11, 8, 16, 12, 7, 9, 14, 23, 4, 7, 9, 14, 4, 6, 11, 10, 12, 4, 10, 12, 4, 19, 7, 15, 12, 73, 26])
-        # fmt: on
+        self.assertListEqual(ids, [4, 30, 4, 20, 7, 12, 4, 25, 8, 13, 9, 4, 10, 9, 4, 9, 10, 9, 5, 6, 22, 4, 6, 20, 8, 4, 6, 11, 8, 16, 12, 7, 9, 14, 23, 4, 7, 9, 14, 4, 6, 11, 10, 12, 4, 10, 12, 4, 19, 7, 15, 12, 73, 26])  # fmt: skip
 
         back_tokens = tokenizer.convert_ids_to_tokens(ids)
-        self.assertListEqual(
-            back_tokens,
-            # fmt: off
-            [SPIECE_UNDERLINE, 'I', SPIECE_UNDERLINE, 'w', 'a', 's', SPIECE_UNDERLINE, 'b', 'o', 'r', 'n', SPIECE_UNDERLINE, 'i', 'n', SPIECE_UNDERLINE, 'n', 'i', 'n', 'e', 't', 'y', SPIECE_UNDERLINE, 't', 'w', 'o', SPIECE_UNDERLINE, 't', 'h', 'o', 'u', 's', 'a', 'n', 'd', ',', SPIECE_UNDERLINE, 'a', 'n', 'd', SPIECE_UNDERLINE, 't', 'h', 'i', 's', SPIECE_UNDERLINE, 'i', 's', SPIECE_UNDERLINE, 'f', 'a', 'l', 's', 'é', '.']
-            # fmt: on
-        )
+        self.assertListEqual(back_tokens,[SPIECE_UNDERLINE, 'I', SPIECE_UNDERLINE, 'w', 'a', 's', SPIECE_UNDERLINE, 'b', 'o', 'r', 'n', SPIECE_UNDERLINE, 'i', 'n', SPIECE_UNDERLINE, 'n', 'i', 'n', 'e', 't', 'y', SPIECE_UNDERLINE, 't', 'w', 'o', SPIECE_UNDERLINE, 't', 'h', 'o', 'u', 's', 'a', 'n', 'd', ',', SPIECE_UNDERLINE, 'a', 'n', 'd', SPIECE_UNDERLINE, 't', 'h', 'i', 's', SPIECE_UNDERLINE, 'i', 's', SPIECE_UNDERLINE, 'f', 'a', 'l', 's', 'é', '.'])  # fmt: skip
 
     @slow
     def test_tokenizer_integration(self):

tests/models/switch_transformers/test_modeling_switch_transformers.py

@@ -905,6 +905,7 @@ class SwitchTransformerRouterTest(unittest.TestCase):
     Original implementation of the routers here:
 
     """
+
     config = SwitchTransformersConfig(
         num_experts=2,
         hidden_size=8,

tests/models/t5/test_tokenization_t5.py

@@ -369,9 +369,7 @@ class T5TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
 
     @slow
     def test_tokenizer_integration(self):
-        # fmt: off
-        expected_encoding = {'input_ids': [[31220, 7, 41, 14034, 801, 38, 3, 102, 63, 17, 127, 524, 18, 7031, 2032, 277, 11, 3, 102, 63, 17, 127, 524, 18, 2026, 17, 10761, 18, 7041, 61, 795, 879, 18, 19681, 4648, 7, 41, 12920, 382, 6, 350, 6383, 4949, 6, 2158, 12920, 382, 9, 6, 3, 4, 11160, 6, 2043, 17153, 279, 49, 17, 6, 3, 4, 434, 9688, 11439, 21, 6869, 10509, 17725, 41, 567, 9138, 61, 11, 6869, 10509, 11946, 41, 18207, 517, 61, 28, 147, 3538, 1220, 7140, 10761, 2250, 16, 910, 1220, 8024, 11, 1659, 1413, 32, 883, 2020, 344, 2215, 226, 6, 12901, 382, 127, 524, 11, 4738, 7, 127, 15390, 5, 1], [272, 24203, 19, 876, 12, 554, 18, 9719, 1659, 2647, 26352, 6497, 7, 45, 73, 9339, 400, 26, 1499, 57, 22801, 10760, 30, 321, 646, 11, 269, 2625, 16, 66, 7500, 5, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [37, 1704, 4216, 3, 20400, 4418, 7, 147, 8, 19743, 1782, 5, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]], 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]]}  # noqa: E501
-        # fmt: on
+        expected_encoding = {'input_ids': [[31220, 7, 41, 14034, 801, 38, 3, 102, 63, 17, 127, 524, 18, 7031, 2032, 277, 11, 3, 102, 63, 17, 127, 524, 18, 2026, 17, 10761, 18, 7041, 61, 795, 879, 18, 19681, 4648, 7, 41, 12920, 382, 6, 350, 6383, 4949, 6, 2158, 12920, 382, 9, 6, 3, 4, 11160, 6, 2043, 17153, 279, 49, 17, 6, 3, 4, 434, 9688, 11439, 21, 6869, 10509, 17725, 41, 567, 9138, 61, 11, 6869, 10509, 11946, 41, 18207, 517, 61, 28, 147, 3538, 1220, 7140, 10761, 2250, 16, 910, 1220, 8024, 11, 1659, 1413, 32, 883, 2020, 344, 2215, 226, 6, 12901, 382, 127, 524, 11, 4738, 7, 127, 15390, 5, 1], [272, 24203, 19, 876, 12, 554, 18, 9719, 1659, 2647, 26352, 6497, 7, 45, 73, 9339, 400, 26, 1499, 57, 22801, 10760, 30, 321, 646, 11, 269, 2625, 16, 66, 7500, 5, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [37, 1704, 4216, 3, 20400, 4418, 7, 147, 8, 19743, 1782, 5, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]], 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]]}  # fmt: skip
 
         self.tokenizer_integration_test_util(
             expected_encoding=expected_encoding,

tests/models/tapas/test_tokenization_tapas.py

@@ -1214,9 +1214,7 @@ class TapasTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
 
         tokenizer = TapasTokenizer.from_pretrained("google/tapas-base-finetuned-wtq", model_max_length=512)
 
-        # fmt: off
-        expected_results = {'input_ids':[101,2043,2001,8226,15091,2141,1029,102,5889,2287,2193,1997,5691,3058,1997,4182,8226,15091,5179,6584,2324,2285,3699,14720,4487,6178,9488,3429,5187,2340,2281,3326,2577,18856,7828,3240,5354,6353,1020,2089,3777],'attention_mask':[1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1],'token_type_ids':[[0,0,0,0,0,0,0],[0,0,0,0,0,0,0],[0,0,0,0,0,0,0],[0,0,0,0,0,0,0],[0,0,0,0,0,0,0],[0,0,0,0,0,0,0],[0,0,0,0,0,0,0],[0,0,0,0,0,0,0],[1,1,0,0,0,0,0],[1,2,0,0,0,0,0],[1,3,0,0,0,0,0],[1,3,0,0,0,0,0],[1,3,0,0,0,0,0],[1,4,0,0,0,0,0],[1,4,0,0,0,0,0],[1,4,0,0,0,0,0],[1,1,1,0,0,0,0],[1,1,1,0,0,0,0],[1,2,1,0,2,2,0],[1,3,1,0,3,1,0],[1,4,1,0,2,2,0],[1,4,1,0,2,2,0],[1,4,1,0,2,2,0],[1,1,2,0,0,0,0],[1,1,2,0,0,0,0],[1,1,2,0,0,0,0],[1,1,2,0,0,0,0],[1,2,2,0,1,3,0],[1,3,2,0,1,3,0],[1,4,2,0,3,1,0],[1,4,2,0,3,1,0],[1,4,2,0,3,1,0],[1,1,3,0,0,0,0],[1,1,3,0,0,0,0],[1,1,3,0,0,0,0],[1,1,3,0,0,0,0],[1,2,3,0,3,1,0],[1,3,3,0,2,2,0],[1,4,3,0,1,3,0],[1,4,3,0,1,3,0],[1,4,3,0,1,3,0]]}  # noqa: E231
-        # fmt: on
+        expected_results = {'input_ids':[101,2043,2001,8226,15091,2141,1029,102,5889,2287,2193,1997,5691,3058,1997,4182,8226,15091,5179,6584,2324,2285,3699,14720,4487,6178,9488,3429,5187,2340,2281,3326,2577,18856,7828,3240,5354,6353,1020,2089,3777],'attention_mask':[1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1],'token_type_ids':[[0,0,0,0,0,0,0],[0,0,0,0,0,0,0],[0,0,0,0,0,0,0],[0,0,0,0,0,0,0],[0,0,0,0,0,0,0],[0,0,0,0,0,0,0],[0,0,0,0,0,0,0],[0,0,0,0,0,0,0],[1,1,0,0,0,0,0],[1,2,0,0,0,0,0],[1,3,0,0,0,0,0],[1,3,0,0,0,0,0],[1,3,0,0,0,0,0],[1,4,0,0,0,0,0],[1,4,0,0,0,0,0],[1,4,0,0,0,0,0],[1,1,1,0,0,0,0],[1,1,1,0,0,0,0],[1,2,1,0,2,2,0],[1,3,1,0,3,1,0],[1,4,1,0,2,2,0],[1,4,1,0,2,2,0],[1,4,1,0,2,2,0],[1,1,2,0,0,0,0],[1,1,2,0,0,0,0],[1,1,2,0,0,0,0],[1,1,2,0,0,0,0],[1,2,2,0,1,3,0],[1,3,2,0,1,3,0],[1,4,2,0,3,1,0],[1,4,2,0,3,1,0],[1,4,2,0,3,1,0],[1,1,3,0,0,0,0],[1,1,3,0,0,0,0],[1,1,3,0,0,0,0],[1,1,3,0,0,0,0],[1,2,3,0,3,1,0],[1,3,3,0,2,2,0],[1,4,3,0,1,3,0],[1,4,3,0,1,3,0],[1,4,3,0,1,3,0]]}  # fmt: skip
 
         new_encoded_inputs = tokenizer.encode_plus(table=table, query=queries[0])
 
@@ -1258,9 +1256,7 @@ class TapasTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
         column_ids = token_type_ids[:, 1]
         row_ids = token_type_ids[:, 2]
 
-        # fmt: off
-        expected_results = {'input_ids':[101,2054,2020,1996,6853,3415,1029,102,13433,2015,2053,4062,2136,10876,2051,1013,3394,8370,2685,1015,3590,4754,29267,4765,3771,2136,2447,1005,1055,6584,1015,1024,4466,1024,2340,1012,6185,2509,1015,2570,1016,1015,10391,12022,4226,7895,10625,1013,22996,3868,6584,1009,1014,1012,1022,10819,2015,1016,2459,1017,1017,2703,10555,2136,2447,1005,1055,6584,1009,2654,1012,1020,10819,2015,1017,2403,1018,1023,8709,8183,3126,21351,2078,1010,3781,1012,2136,10958,8865,6584,1009,2871,1012,1022,10819,2015,2410,2260,1019,4090,7986,5292,5677,8151,2771,1011,2990,9187,3868,6584,1009,4413,1012,1015,10819,2015,1020,2184,1020,2322,2030,20282,14262,9035,4754,3868,6584,1009,1015,1024,4002,1012,1016,2184,1022,1021,4868,7918,12023,12023,3868,6584,1009,1015,1024,5890,1012,1018,1019,1020,1022,2260,5261,12436,18116,2137,4382,2136,26447,6584,1009,1015,1024,5890,1012,1022,1022,1019,1023,1021,27339,3995,10125,9711,4906,25101,24657,1011,22033,2386,3868,6564,1009,1015,5001,2321,1018,2184,4583,7986,14383,2075,29488,14906,9351,2971,6564,1009,1015,5001,2340,1017,2340,2676,8527,2014,2696,1052,2243,3868,6564,1009,1015,5001,2260,1016,2260,2861,4575,4477,1011,2128,4710,2137,4382,2136,26447,6564,1009,1015,5001,2459,1015,2410,2539,8963,11503,25457,3022,8512,2522,9654,3868,5594,1009,1016,10876,2324,1014,2403,3943,4074,6415,15204,2072,12496,25378,3868,5594,1009,1016,10876,2403,1014,2321,1018,10704,17921,14906,9351,2971,5594,1009,1016,10876,1023,1014,2385,2340,14915,5795,8512,2522,9654,3868,6640,6228,2539,1014,2459,1016,28328,8945,3126,21351,2015,10625,1013,22996,3868,6255,6228,1018,1014,2324,2321,12270,11956,5232,3868,2260,6228,1021,1014,2539,1019,8473,28027,2080,2474,6371,5232,3868,2184,6228,2385,1014,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],'column_ids':[0,0,0,0,0,0,0,0,1,1,2,3,4,5,6,6,6,7,8,1,2,3,3,3,3,4,4,4,4,5,6,6,6,6,6,6,6,6,7,8,1,2,3,3,3,3,4,4,4,4,5,6,6,6,6,6,6,7,8,1,2,3,3,4,4,4,4,5,6,6,6,6,6,6,7,8,1,2,3,3,3,3,3,3,3,3,4,4,4,5,6,6,6,6,6,6,7,8,1,2,3,3,3,3,4,4,4,4,4,5,6,6,6,6,6,6,7,8,1,2,3,3,3,3,4,4,5,6,6,6,6,6,6,7,8,1,2,3,3,4,4,5,6,6,6,6,6,6,7,8,1,2,3,3,3,4,4,4,4,5,6,6,6,6,6,6,7,8,1,2,3,3,3,3,4,4,4,4,4,4,4,5,6,6,6,7,8,1,2,3,3,3,3,4,4,4,5,6,6,6,7,8,1,2,3,3,3,4,4,4,5,6,6,6,7,8,1,2,3,3,3,3,3,4,4,4,4,5,6,6,6,7,8,1,2,3,3,3,3,4,4,4,4,5,6,6,6,7,8,1,2,3,3,3,3,4,4,4,5,6,6,6,7,8,1,2,3,3,4,4,4,5,6,6,6,7,8,1,2,3,3,4,4,4,4,5,6,7,8,1,2,3,3,3,3,3,4,4,4,4,5,6,7,8,1,2,3,3,4,4,5,6,7,8,1,2,3,3,3,3,3,4,4,5,6,7,8,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],'row_ids':[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,11,11,11,11,11,11,11,11,11,11,11,11,11,11,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,15,15,15,15,15,15,15,15,15,15,15,15,15,16,16,16,16,16,16,16,16,16,16,16,16,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,18,18,18,18,18,18,18,18,18,18,19,19,19,19,19,19,19,19,19,19,19,19,19,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],'segment_ids':[0,0,0,0,0,0,0,0,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0]}  # noqa: E231
-        # fmt: on
+        expected_results = {'input_ids':[101,2054,2020,1996,6853,3415,1029,102,13433,2015,2053,4062,2136,10876,2051,1013,3394,8370,2685,1015,3590,4754,29267,4765,3771,2136,2447,1005,1055,6584,1015,1024,4466,1024,2340,1012,6185,2509,1015,2570,1016,1015,10391,12022,4226,7895,10625,1013,22996,3868,6584,1009,1014,1012,1022,10819,2015,1016,2459,1017,1017,2703,10555,2136,2447,1005,1055,6584,1009,2654,1012,1020,10819,2015,1017,2403,1018,1023,8709,8183,3126,21351,2078,1010,3781,1012,2136,10958,8865,6584,1009,2871,1012,1022,10819,2015,2410,2260,1019,4090,7986,5292,5677,8151,2771,1011,2990,9187,3868,6584,1009,4413,1012,1015,10819,2015,1020,2184,1020,2322,2030,20282,14262,9035,4754,3868,6584,1009,1015,1024,4002,1012,1016,2184,1022,1021,4868,7918,12023,12023,3868,6584,1009,1015,1024,5890,1012,1018,1019,1020,1022,2260,5261,12436,18116,2137,4382,2136,26447,6584,1009,1015,1024,5890,1012,1022,1022,1019,1023,1021,27339,3995,10125,9711,4906,25101,24657,1011,22033,2386,3868,6564,1009,1015,5001,2321,1018,2184,4583,7986,14383,2075,29488,14906,9351,2971,6564,1009,1015,5001,2340,1017,2340,2676,8527,2014,2696,1052,2243,3868,6564,1009,1015,5001,2260,1016,2260,2861,4575,4477,1011,2128,4710,2137,4382,2136,26447,6564,1009,1015,5001,2459,1015,2410,2539,8963,11503,25457,3022,8512,2522,9654,3868,5594,1009,1016,10876,2324,1014,2403,3943,4074,6415,15204,2072,12496,25378,3868,5594,1009,1016,10876,2403,1014,2321,1018,10704,17921,14906,9351,2971,5594,1009,1016,10876,1023,1014,2385,2340,14915,5795,8512,2522,9654,3868,6640,6228,2539,1014,2459,1016,28328,8945,3126,21351,2015,10625,1013,22996,3868,6255,6228,1018,1014,2324,2321,12270,11956,5232,3868,2260,6228,1021,1014,2539,1019,8473,28027,2080,2474,6371,5232,3868,2184,6228,2385,1014,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],'column_ids':[0,0,0,0,0,0,0,0,1,1,2,3,4,5,6,6,6,7,8,1,2,3,3,3,3,4,4,4,4,5,6,6,6,6,6,6,6,6,7,8,1,2,3,3,3,3,4,4,4,4,5,6,6,6,6,6,6,7,8,1,2,3,3,4,4,4,4,5,6,6,6,6,6,6,7,8,1,2,3,3,3,3,3,3,3,3,4,4,4,5,6,6,6,6,6,6,7,8,1,2,3,3,3,3,4,4,4,4,4,5,6,6,6,6,6,6,7,8,1,2,3,3,3,3,4,4,5,6,6,6,6,6,6,7,8,1,2,3,3,4,4,5,6,6,6,6,6,6,7,8,1,2,3,3,3,4,4,4,4,5,6,6,6,6,6,6,7,8,1,2,3,3,3,3,4,4,4,4,4,4,4,5,6,6,6,7,8,1,2,3,3,3,3,4,4,4,5,6,6,6,7,8,1,2,3,3,3,4,4,4,5,6,6,6,7,8,1,2,3,3,3,3,3,4,4,4,4,5,6,6,6,7,8,1,2,3,3,3,3,4,4,4,4,5,6,6,6,7,8,1,2,3,3,3,3,4,4,4,5,6,6,6,7,8,1,2,3,3,4,4,4,5,6,6,6,7,8,1,2,3,3,4,4,4,4,5,6,7,8,1,2,3,3,3,3,3,4,4,4,4,5,6,7,8,1,2,3,3,4,4,5,6,7,8,1,2,3,3,3,3,3,4,4,5,6,7,8,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],'row_ids':[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,11,11,11,11,11,11,11,11,11,11,11,11,11,11,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,15,15,15,15,15,15,15,15,15,15,15,15,15,16,16,16,16,16,16,16,16,16,16,16,16,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,18,18,18,18,18,18,18,18,18,18,19,19,19,19,19,19,19,19,19,19,19,19,19,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],'segment_ids':[0,0,0,0,0,0,0,0,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0]}  # fmt: skip
 
         self.assertListEqual(input_ids, expected_results["input_ids"])
         self.assertListEqual(segment_ids.tolist(), expected_results["segment_ids"])

tests/models/transfo_xl/test_modeling_tf_transfo_xl.py

@@ -251,9 +251,7 @@ class TFTransfoXLModelLanguageGenerationTest(unittest.TestCase):
     @slow
     def test_lm_generate_transfo_xl_wt103(self):
         model = TFTransfoXLLMHeadModel.from_pretrained("transfo-xl-wt103")
-        # fmt: off
-        input_ids = tf.convert_to_tensor([[33,1297,2,1,1009,4,1109,11739,4762,358,5,25,245,22,1706,17,20098,5,3215,21,37,1110,3,13,1041,4,24,603,490,2,71477,20098,104447,2,20961,1,2604,4,1,329,3,6224,831,16002,2,8,603,78967,29546,23,803,20,25,416,5,8,232,4,277,6,1855,4601,3,29546,54,8,3609,5,57211,49,4,1,277,18,8,1755,15691,3,341,25,416,693,42573,71,17,401,94,31,17919,2,29546,7873,18,1,435,23,11011,755,5,5167,3,7983,98,84,2,29546,3267,8,3609,4,1,4865,1075,2,6087,71,6,346,8,5854,3,29546,824,1400,1868,2,19,160,2,311,8,5496,2,20920,17,25,15097,3,24,24,0]],dtype=tf.int32)  # noqa: E231
-        # fmt: on
+        input_ids = tf.convert_to_tensor([[33, 1297, 2, 1, 1009, 4, 1109, 11739, 4762, 358, 5, 25, 245, 22, 1706, 17, 20098, 5, 3215, 21, 37, 1110, 3, 13, 1041, 4, 24, 603, 490, 2, 71477, 20098, 104447, 2, 20961, 1, 2604, 4, 1, 329, 3, 6224, 831, 16002, 2, 8, 603, 78967, 29546, 23, 803, 20, 25, 416, 5, 8, 232, 4, 277, 6, 1855, 4601, 3, 29546, 54, 8, 3609, 5, 57211, 49, 4, 1, 277, 18, 8, 1755, 15691, 3, 341, 25, 416, 693, 42573, 71, 17, 401, 94, 31, 17919, 2, 29546, 7873, 18, 1, 435, 23, 11011, 755, 5, 5167, 3, 7983, 98, 84, 2, 29546, 3267, 8, 3609, 4, 1, 4865, 1075, 2, 6087, 71, 6, 346, 8, 5854, 3, 29546, 824, 1400, 1868, 2, 19, 160, 2, 311, 8, 5496, 2, 20920, 17, 25, 15097, 3, 24, 24, 0]])  # fmt: skip
         #  In 1991 , the remains of Russian Tsar Nicholas II and his family
         #  ( except for Alexei and Maria ) are discovered .
         #  The voice of Nicholas's young son , Tsarevich Alexei Nikolaevich , narrates the
@@ -265,22 +263,20 @@ class TFTransfoXLModelLanguageGenerationTest(unittest.TestCase):
         #  the Virgin Mary , prompting him to become a priest . Rasputin quickly becomes famous ,
         #  with people , even a bishop , begging for his blessing . <eod> </s> <eos>
 
-        # fmt: off
-        expected_output_ids = [33,1297,2,1,1009,4,1109,11739,4762,358,5,25,245,22,1706,17,20098,5,3215,21,37,1110,3,13,1041,4,24,603,490,2,71477,20098,104447,2,20961,1,2604,4,1,329,3,6224,831,16002,2,8,603,78967,29546,23,803,20,25,416,5,8,232,4,277,6,1855,4601,3,29546,54,8,3609,5,57211,49,4,1,277,18,8,1755,15691,3,341,25,416,693,42573,71,17,401,94,31,17919,2,29546,7873,18,1,435,23,11011,755,5,5167,3,7983,98,84,2,29546,3267,8,3609,4,1,4865,1075,2,6087,71,6,346,8,5854,3,29546,824,1400,1868,2,19,160,2,311,8,5496,2,20920,17,25,15097,3,24,24,0,33,1,1857,2,1,1009,4,1109,11739,4762,358,5,25,245,28,1110,3,13,1041,4,24,603,490,2,71477,20098,104447,2,20961,1,2604,4,1,329,3,0]  # noqa: E231
-        # fmt: on
-        #  In 1991, the remains of Russian Tsar Nicholas II and his family (
-        #  except for Alexei and Maria ) are discovered. The voice of young son,
-        #  Tsarevich Alexei Nikolaevich, narrates the remainder of the story.
-        #  1883 Western Siberia, a young Grigori Rasputin is asked by his father
-        #  and a group of men to perform magic. Rasputin has a vision and
-        #  denounces one of the men as a horse thief. Although his father initially
-        #  slaps him for making such an accusation, Rasputin watches as the man
-        #  is chased outside and beaten. Twenty years later, Rasputin sees a vision
-        #  of the Virgin Mary, prompting him to become a priest.
-        #  Rasputin quickly becomes famous, with people, even a bishop, begging for
-        #  his blessing. <unk> <unk> <eos> In the 1990s, the remains of Russian Tsar
-        # Nicholas II and his family were discovered. The voice of <unk> young son,
-        # Tsarevich Alexei Nikolaevich, narrates the remainder of the story.<eos>
+        expected_output_ids = [33,1297,2,1,1009,4,1109,11739,4762,358,5,25,245,22,1706,17,20098,5,3215,21,37,1110,3,13,1041,4,24,603,490,2,71477,20098,104447,2,20961,1,2604,4,1,329,3,6224,831,16002,2,8,603,78967,29546,23,803,20,25,416,5,8,232,4,277,6,1855,4601,3,29546,54,8,3609,5,57211,49,4,1,277,18,8,1755,15691,3,341,25,416,693,42573,71,17,401,94,31,17919,2,29546,7873,18,1,435,23,11011,755,5,5167,3,7983,98,84,2,29546,3267,8,3609,4,1,4865,1075,2,6087,71,6,346,8,5854,3,29546,824,1400,1868,2,19,160,2,311,8,5496,2,20920,17,25,15097,3,24,24,0,33,1,142,1298,188,2,29546,113,8,3654,4,1,1109,7136,833,3,13,1645,4,29546,11,104,7,1,1109,532,7129,2,10,83507,2,1162,1123,2,6,7245,10,2,5,11,104,7,1,1109,532,7129,2,10,24,24,10,22,10,13,770,5863,4,7245,10]  # fmt: skip
+        #  In 1991, the remains of Russian Tsar Nicholas II and his family ( except for
+        #  Alexei and Maria ) are discovered. The voice of young son, Tsarevich Alexei
+        #  Nikolaevich, narrates the remainder of the story. 1883 Western Siberia, a young
+        #  Grigori Rasputin is asked by his father and a group of men to perform magic.
+        #  Rasputin has a vision and denounces one of the men as a horse thief. Although
+        #  his father initially slaps him for making such an accusation, Rasputin watches
+        #  as the man is chased outside and beaten. Twenty years later, Rasputin sees a
+        #  vision of the Virgin Mary, prompting him to become a priest. Rasputin quickly
+        #  becomes famous, with people, even a bishop, begging for his blessing. In the
+        #  early 20th century, Rasputin became a symbol of the Russian Orthodox Church.
+        #  The image of Rasputin was used in the Russian national anthem, " Nearer, My God,
+        #  to Heaven ", and was used in the Russian national anthem, " " ( " The Great Spirit
+        #  of Heaven "
 
         output_ids = model.generate(input_ids, max_length=200, do_sample=False)
         self.assertListEqual(output_ids[0].numpy().tolist(), expected_output_ids)

tests/models/transfo_xl/test_modeling_transfo_xl.py

@@ -502,9 +502,7 @@ class TransfoXLModelLanguageGenerationTest(unittest.TestCase):
         model = TransfoXLLMHeadModel.from_pretrained("transfo-xl-wt103")
         model.to(torch_device)
 
-        # fmt: off
-        input_ids = torch.tensor([[33,1297,2,1,1009,4,1109,11739,4762,358,5,25,245,22,1706,17,20098,5,3215,21,37,1110,3,13,1041,4,24,603,490,2,71477,20098,104447,2,20961,1,2604,4,1,329,3,6224,831,16002,2,8,603,78967,29546,23,803,20,25,416,5,8,232,4,277,6,1855,4601,3,29546,54,8,3609,5,57211,49,4,1,277,18,8,1755,15691,3,341,25,416,693,42573,71,17,401,94,31,17919,2,29546,7873,18,1,435,23,11011,755,5,5167,3,7983,98,84,2,29546,3267,8,3609,4,1,4865,1075,2,6087,71,6,346,8,5854,3,29546,824,1400,1868,2,19,160,2,311,8,5496,2,20920,17,25,15097,3,24,24,0]],dtype=torch.long,device=torch_device)  # noqa: E231
-        # fmt: on
+        input_ids = torch.tensor([[33, 1297, 2, 1, 1009, 4, 1109, 11739, 4762, 358, 5, 25, 245, 22, 1706, 17, 20098, 5, 3215, 21, 37, 1110, 3, 13, 1041, 4, 24, 603, 490, 2, 71477, 20098, 104447, 2, 20961, 1, 2604, 4, 1, 329, 3, 6224, 831, 16002, 2, 8, 603, 78967, 29546, 23, 803, 20, 25, 416, 5, 8, 232, 4, 277, 6, 1855, 4601, 3, 29546, 54, 8, 3609, 5, 57211, 49, 4, 1, 277, 18, 8, 1755, 15691, 3, 341, 25, 416, 693, 42573, 71, 17, 401, 94, 31, 17919, 2, 29546, 7873, 18, 1, 435, 23, 11011, 755, 5, 5167, 3, 7983, 98, 84, 2, 29546, 3267, 8, 3609, 4, 1, 4865, 1075, 2, 6087, 71, 6, 346, 8, 5854, 3, 29546, 824, 1400, 1868, 2, 19, 160, 2, 311, 8, 5496, 2, 20920, 17, 25, 15097, 3, 24, 24, 0]], dtype=torch.long,device=torch_device)  # fmt: skip
         #  In 1991 , the remains of Russian Tsar Nicholas II and his family
         #  ( except for Alexei and Maria ) are discovered .
         #  The voice of Nicholas's young son , Tsarevich Alexei Nikolaevich , narrates the
@@ -516,9 +514,7 @@ class TransfoXLModelLanguageGenerationTest(unittest.TestCase):
         #  the Virgin Mary , prompting him to become a priest . Rasputin quickly becomes famous ,
         #  with people , even a bishop , begging for his blessing . <eod> </s> <eos>
 
-        # fmt: off
-        expected_output_ids = [33,1297,2,1,1009,4,1109,11739,4762,358,5,25,245,22,1706,17,20098,5,3215,21,37,1110,3,13,1041,4,24,603,490,2,71477,20098,104447,2,20961,1,2604,4,1,329,3,6224,831,16002,2,8,603,78967,29546,23,803,20,25,416,5,8,232,4,277,6,1855,4601,3,29546,54,8,3609,5,57211,49,4,1,277,18,8,1755,15691,3,341,25,416,693,42573,71,17,401,94,31,17919,2,29546,7873,18,1,435,23,11011,755,5,5167,3,7983,98,84,2,29546,3267,8,3609,4,1,4865,1075,2,6087,71,6,346,8,5854,3,29546,824,1400,1868,2,19,160,2,311,8,5496,2,20920,17,25,15097,3,24,24,0,33,1,142,1298,188,2,29546,113,8,3654,4,1,1109,7136,833,3,13,1645,4,29546,11,104,7,1,1109,532,7129,2,10,83507,2,1162,1123,2,6,7245,10,2,5,11,104,7,1,1109,532,7129,2,10,24,24,10,22,10,13,770,5863,4,7245,10]  # noqa: E231
-        # fmt: on
+        expected_output_ids = [33,1297,2,1,1009,4,1109,11739,4762,358,5,25,245,22,1706,17,20098,5,3215,21,37,1110,3,13,1041,4,24,603,490,2,71477,20098,104447,2,20961,1,2604,4,1,329,3,6224,831,16002,2,8,603,78967,29546,23,803,20,25,416,5,8,232,4,277,6,1855,4601,3,29546,54,8,3609,5,57211,49,4,1,277,18,8,1755,15691,3,341,25,416,693,42573,71,17,401,94,31,17919,2,29546,7873,18,1,435,23,11011,755,5,5167,3,7983,98,84,2,29546,3267,8,3609,4,1,4865,1075,2,6087,71,6,346,8,5854,3,29546,824,1400,1868,2,19,160,2,311,8,5496,2,20920,17,25,15097,3,24,24,0,33,1,142,1298,188,2,29546,113,8,3654,4,1,1109,7136,833,3,13,1645,4,29546,11,104,7,1,1109,532,7129,2,10,83507,2,1162,1123,2,6,7245,10,2,5,11,104,7,1,1109,532,7129,2,10,24,24,10,22,10,13,770,5863,4,7245,10]  # fmt: skip
         #  In 1991, the remains of Russian Tsar Nicholas II and his family ( except for
         #  Alexei and Maria ) are discovered. The voice of young son, Tsarevich Alexei
         #  Nikolaevich, narrates the remainder of the story. 1883 Western Siberia, a young

tests/models/vision_encoder_decoder/test_modeling_tf_vision_encoder_decoder.py

@@ -407,7 +407,7 @@ class TFVisionEncoderDecoderMixin:
     def prepare_pt_inputs_from_tf_inputs(self, tf_inputs_dict):
         pt_inputs_dict = {}
         for name, key in tf_inputs_dict.items():
-            if type(key) == bool:
+            if isinstance(key, bool):
                 pt_inputs_dict[name] = key
             elif name == "input_values":
                 pt_inputs_dict[name] = torch.from_numpy(key.numpy()).to(torch.float32)

tests/models/vision_encoder_decoder/test_modeling_vision_encoder_decoder.py

@@ -928,9 +928,7 @@ class DonutModelIntegrationTest(unittest.TestCase):
         sequence = re.sub(r"<.*?>", "", sequence, count=1).strip()  # remove first task start token
 
         # verify generated sequence
-        # fmt: off
-        expected_sequence = "<s_menu><s_nm> CINNAMON SUGAR</s_nm><s_unitprice> 17,000</s_unitprice><s_cnt> 1 x</s_cnt><s_price> 17,000</s_price></s_menu><s_sub_total><s_subtotal_price> 17,000</s_subtotal_price></s_sub_total><s_total><s_total_price> 17,000</s_total_price><s_cashprice> 20,000</s_cashprice><s_changeprice> 3,000</s_changeprice></s_total>"  # noqa: E231
-        # fmt: on
+        expected_sequence = "<s_menu><s_nm> CINNAMON SUGAR</s_nm><s_unitprice> 17,000</s_unitprice><s_cnt> 1 x</s_cnt><s_price> 17,000</s_price></s_menu><s_sub_total><s_subtotal_price> 17,000</s_subtotal_price></s_sub_total><s_total><s_total_price> 17,000</s_total_price><s_cashprice> 20,000</s_cashprice><s_changeprice> 3,000</s_changeprice></s_total>"  # noqa: E231  # fmt: skip
         self.assertEqual(sequence, expected_sequence)
 
         # verify scores

tests/models/vision_text_dual_encoder/test_processor_vision_text_dual_encoder.py

@@ -38,9 +38,7 @@ class VisionTextDualEncoderProcessorTest(unittest.TestCase):
     def setUp(self):
         self.tmpdirname = tempfile.mkdtemp()
 
-        # fmt: off
-        vocab_tokens = ["[UNK]", "[CLS]", "[SEP]", "[PAD]", "[MASK]", "want", "##want", "##ed", "wa", "un", "runn", "##ing", ",", "low", "lowest"]
-        # fmt: on
+        vocab_tokens = ["[UNK]", "[CLS]", "[SEP]", "[PAD]", "[MASK]", "want", "##want", "##ed", "wa", "un", "runn", "##ing", ",", "low", "lowest"]  # fmt: skip
         self.vocab_file = os.path.join(self.tmpdirname, VOCAB_FILES_NAMES["vocab_file"])
         with open(self.vocab_file, "w", encoding="utf-8") as vocab_writer:
             vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))

tests/models/wav2vec2/test_modeling_tf_wav2vec2.py

@@ -850,8 +850,9 @@ class TFWav2Vec2ModelIntegrationTest(unittest.TestCase):
         input_values = inputs.input_values
         attention_mask = inputs.attention_mask
         outputs = model(input_values, attention_mask)
-        predicted_logits, predicted_ids = tf.math.reduce_max(outputs.logits, axis=-1), tf.argmax(
-            outputs.logits, axis=-1
+        predicted_logits, predicted_ids = (
+            tf.math.reduce_max(outputs.logits, axis=-1),
+            tf.argmax(outputs.logits, axis=-1),
         )
         expected_labels = [7, 6, 10, 9]
         expected_logits = tf.convert_to_tensor([6.1186, 11.8961, 10.2931, 6.0898])
@@ -866,15 +867,18 @@ class TFWav2Vec2ModelIntegrationTest(unittest.TestCase):
         input_values = inputs.input_values
         attention_mask = inputs.attention_mask
         outputs = model(input_values, attention_mask=attention_mask)
-        predicted_logits_action, predicted_ids_action = tf.math.reduce_max(outputs.logits[:, :6], axis=-1), tf.argmax(
-            outputs.logits[:, :6], axis=-1
+        predicted_logits_action, predicted_ids_action = (
+            tf.math.reduce_max(outputs.logits[:, :6], axis=-1),
+            tf.argmax(outputs.logits[:, :6], axis=-1),
+        )
+        predicted_logits_object, predicted_ids_object = (
+            tf.math.reduce_max(outputs.logits[:, 6:20], axis=-1),
+            tf.argmax(outputs.logits[:, 6:20], axis=-1),
+        )
+        predicted_logits_location, predicted_ids_location = (
+            tf.math.reduce_max(outputs.logits[:, 20:24], axis=-1),
+            tf.argmax(outputs.logits[:, 20:24], axis=-1),
         )
-        predicted_logits_object, predicted_ids_object = tf.math.reduce_max(
-            outputs.logits[:, 6:20], axis=-1
-        ), tf.argmax(outputs.logits[:, 6:20], axis=-1)
-        predicted_logits_location, predicted_ids_location = tf.math.reduce_max(
-            outputs.logits[:, 20:24], axis=-1
-        ), tf.argmax(outputs.logits[:, 20:24], axis=-1)
         expected_labels_action = [0, 0, 2, 3]
         expected_logits_action = tf.convert_to_tensor([0.4568, 11.0848, 1.6621, 9.3841])
         expected_labels_object = [3, 10, 3, 4]
@@ -915,8 +919,9 @@ class TFWav2Vec2ModelIntegrationTest(unittest.TestCase):
         input_values = inputs.input_values
         attention_mask = inputs.attention_mask
         outputs = model(input_values, attention_mask=attention_mask)
-        predicted_logits, predicted_ids = tf.math.reduce_max(outputs.logits, axis=-1), tf.argmax(
-            outputs.logits, axis=-1
+        predicted_logits, predicted_ids = (
+            tf.math.reduce_max(outputs.logits, axis=-1),
+            tf.argmax(outputs.logits, axis=-1),
         )
 
         expected_labels = [1, 1, 2, 2]

tests/models/whisper/test_modeling_flax_whisper.py

@@ -670,9 +670,7 @@ class FlaxWhisperModelIntegrationTest(unittest.TestCase):
 
         generated_ids = generate_fn(input_features)
 
-        # fmt: off
-        EXPECTED_OUTPUT = np.array([50258, 50259, 50359, 50364, 2221, 13, 2326, 388, 391, 307, 264, 50244, 295, 264, 2808, 5359, 11, 293, 321, 366, 5404, 281, 2928, 702, 14943, 13, 50692, 50692, 6966, 307, 2221, 13, 2326, 388, 391, 311, 9060, 1570, 1880, 813, 702, 1871, 13, 50926, 50926, 634, 5112, 505, 300, 412, 341, 42729, 3196, 295, 264, 1064, 11, 365, 5272, 293, 12904, 9256, 450, 10539, 51208, 51208, 949, 505, 11, 14138, 10117, 490, 3936, 293, 1080, 3542, 5160, 881, 26336, 281, 264, 1575, 13, 51552, 51552, 634, 575, 12525, 22618, 1968, 6144, 35617, 7354, 1292, 6, 589, 307, 534, 10281, 934, 439, 11, 293, 51836, 51836, 50257])
-        # fmt: on
+        EXPECTED_OUTPUT = np.array([50258, 50259, 50359, 50364, 2221, 13, 2326, 388, 391, 307, 264, 50244, 295, 264, 2808, 5359, 11, 293, 321, 366, 5404, 281, 2928, 702, 14943, 13, 50692, 50692, 6966, 307, 2221, 13, 2326, 388, 391, 311, 9060, 1570, 1880, 813, 702, 1871, 13, 50926, 50926, 634, 5112, 505, 300, 412, 341, 42729, 3196, 295, 264, 1064, 11, 365, 5272, 293, 12904, 9256, 450, 10539, 51208, 51208, 949, 505, 11, 14138, 10117, 490, 3936, 293, 1080, 3542, 5160, 881, 26336, 281, 264, 1575, 13, 51552, 51552, 634, 575, 12525, 22618, 1968, 6144, 35617, 7354, 1292, 6, 589, 307, 534, 10281, 934, 439, 11, 293, 51836, 51836, 50257])  # fmt: skip
 
         self.assertTrue(np.allclose(generated_ids, EXPECTED_OUTPUT))