SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Skip tests properly (#31308)

Browse Source 
* Skip tests properly

* [test_all]

* Add 'reason' as kwarg for skipTest

* [test_all] Fix up

* [test_all]
This commit is contained in:
amyeroberts
2024-06-26 21:59:08 +01:00
committed by GitHub
parent 1f9f57ab4c
commit 1de7dc7403
254 changed files with 1721 additions and 1298 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
tests/models/seamless_m4t/test_tokenization_seamless_m4t.py
View File

@@ -141,7 +141,7 @@ class SeamlessM4TTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
],
)
@unittest.skip("This fails currently and is a blocker. No idea why TODO @ylacombe")
@unittest.skip(reason="This fails currently and is a blocker. No idea why TODO @ylacombe")
def test_maximum_encoding_length_single_input(self):
tokenizers = self.get_tokenizers(do_lower_case=False, model_max_length=100)
for tokenizer in tokenizers:
@@ -244,7 +244,7 @@ class SeamlessM4TTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
self.assertEqual(len(overflowing_tokens), 2 + stride)
self.assertEqual(overflowing_tokens, sequence[-(2 + stride) :])
@unittest.skip("By defaults, uses pad_to_multiple_of which breaks the test")
@unittest.skip(reason="By defaults, uses pad_to_multiple_of which breaks the test")
def test_maximum_encoding_length_pair_input(self):
pass
@@ -253,7 +253,7 @@ class SeamlessM4TTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
for tokenizer in tokenizers:
with self.subTest(f"{tokenizer.__class__.__name__}"):
if tokenizer.pad_token is None:
self.skipTest("No padding token.")
self.skipTest(reason="No padding token.")
else:
empty_tokens = tokenizer("", padding=True, pad_to_multiple_of=8)
normal_tokens = tokenizer("This is a sample input", padding=True, pad_to_multiple_of=8)
@@ -286,7 +286,7 @@ class SeamlessM4TTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
@require_torch
def test_prepare_seq2seq_batch(self):
if not self.test_seq2seq:
return
self.skipTest(reason="test_seq2seq is set to False")
tokenizers = self.get_tokenizers()
for tokenizer in tokenizers:
@@ -316,7 +316,7 @@ class SeamlessM4TTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
pad_to_multiple_of=None,
)
except NotImplementedError:
return
self.skipTest(reason="Encountered NotImplementedError when calling prepare_seq2seq_batch")
self.assertEqual(batch.input_ids.shape[1], 3)
self.assertEqual(batch.labels.shape[1], 10)
@@ -343,7 +343,7 @@ class SeamlessM4TTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
self.assertEqual(batch_encoder_only.attention_mask.shape[1], 4)
self.assertNotIn("decoder_input_ids", batch_encoder_only)
@unittest.skip("Unfortunately way too slow to build a BPE with SentencePiece.")
@unittest.skip(reason="Unfortunately way too slow to build a BPE with SentencePiece.")
def test_save_slow_from_fast_and_reload_fast(self):
pass
@@ -390,7 +390,7 @@ class SeamlessM4TTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
def test_training_new_tokenizer(self):
# This feature only exists for fast tokenizers
if not self.test_rust_tokenizer:
return
self.skipTest(reason="test_rust_tokenizer is set to False")
tokenizer = self.get_rust_tokenizer()
new_tokenizer = tokenizer.train_new_from_iterator(SMALL_TRAINING_CORPUS, 100)
@@ -425,11 +425,11 @@ class SeamlessM4TTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
self.assertDictEqual(tokenizer.special_tokens_map, new_tokenizer.special_tokens_map)
@unittest.skip("Fails because of the hack of adding <unk> in _tokenize")
@unittest.skip(reason="Fails because of the hack of adding <unk> in _tokenize")
def test_pickle_subword_regularization_tokenizer(self):
pass
@unittest.skip("Fails because of the hack of adding <unk> in _tokenize")
@unittest.skip(reason="Fails because of the hack of adding <unk> in _tokenize")
def test_subword_regularization_tokenizer(self):
pass