wehub-resource-sync
e06fe8e8c6
Self-hosted runner (benchmark) / Benchmark (aws-g5-4xlarge-cache) (push) Waiting to run
New model PR merged notification / Notify new model (push) Waiting to run
Update Transformers metadata / build_and_package (push) Waiting to run
Secret Leaks / trufflehog (push) Failing after 1s
Build documentation / build (push) Failing after 1s
Build documentation / build_other_lang (push) Failing after 0s
CodeQL Security Analysis / CodeQL Analysis (push) Failing after 0s
PR CI / pr-ci (push) Failing after 1s
Slow tests on important models (on Push - A10) / Get all modified files (push) Failing after 1s
Slow tests on important models (on Push - A10) / Model CI (push) Has been skipped
40 lines
1.7 KiB
Python
40 lines
1.7 KiB
Python
import unittest
|
|
import warnings
|
|
from dataclasses import dataclass
|
|
|
|
from transformers.convert_slow_tokenizer import SpmConverter
|
|
from transformers.testing_utils import get_tests_dir
|
|
|
|
|
|
@dataclass
|
|
class FakeOriginalTokenizer:
|
|
vocab_file: str
|
|
|
|
|
|
class ConvertSlowTokenizerTest(unittest.TestCase):
|
|
def test_spm_converter_bytefallback_warning(self):
|
|
spm_model_file_without_bytefallback = get_tests_dir("fixtures/test_sentencepiece.model")
|
|
spm_model_file_with_bytefallback = get_tests_dir("fixtures/test_sentencepiece_with_bytefallback.model")
|
|
|
|
original_tokenizer_without_bytefallback = FakeOriginalTokenizer(vocab_file=spm_model_file_without_bytefallback)
|
|
|
|
with warnings.catch_warnings(record=True) as w:
|
|
_ = SpmConverter(original_tokenizer_without_bytefallback)
|
|
# We are looking for if there is any `UserWarning` with
|
|
# `The sentencepiece tokenizer that you are converting to a fast tokenizer uses the byte fallback option which is not implemented in the fast tokenizers.`
|
|
w = [x for x in w if x.category.__name__ != "DeprecationWarning"]
|
|
self.assertEqual(len(w), 0)
|
|
|
|
original_tokenizer_with_bytefallback = FakeOriginalTokenizer(vocab_file=spm_model_file_with_bytefallback)
|
|
|
|
with warnings.catch_warnings(record=True) as w:
|
|
_ = SpmConverter(original_tokenizer_with_bytefallback)
|
|
w = [x for x in w if x.category.__name__ != "DeprecationWarning"]
|
|
self.assertEqual(len(w), 1)
|
|
|
|
self.assertIn(
|
|
"The sentencepiece tokenizer that you are converting to a fast tokenizer uses the byte fallback option"
|
|
" which is not implemented in the fast tokenizers.",
|
|
str(w[0].message),
|
|
)
|