mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-04 13:20:12 +06:00
19420fd99e
* move test model folders (TODO: fix imports and others) * fix (potentially partially) imports (in model test modules) * fix (potentially partially) imports (in tokenization test modules) * fix (potentially partially) imports (in feature extraction test modules) * fix import utils.test_modeling_tf_core * fix path ../fixtures/ * fix imports about generation.test_generation_flax_utils * fix more imports * fix fixture path * fix get_test_dir * update module_to_test_file * fix get_tests_dir from wrong transformers.utils * update config.yml (CircleCI) * fix style * remove missing imports * update new model script * update check_repo * update SPECIAL_MODULE_TO_TEST_MAP * fix style * add __init__ * update self-scheduled * fix add_new_model scripts * check one way to get location back * python setup.py build install * fix import in test auto * update self-scheduled.yml * update slack notification script * Add comments about artifact names * fix for yolos Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
37 lines
1.4 KiB
Python
37 lines
1.4 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)
|
|
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)
|
|
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),
|
|
)
|