06f1fd69a6
Some checks failed
Self-hosted runner (nightly-past-ci-caller) / Get number (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.11 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.10 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.9 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.8 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.7 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.6 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.5 (push) Has been cancelled
Self-hosted runner (benchmark) / Benchmark (aws-g5-4xlarge-cache) (push) Has been cancelled
Build documentation / build (push) Has been cancelled
Build documentation / build_other_lang (push) Has been cancelled
CodeQL Security Analysis / CodeQL Analysis (push) Has been cancelled
New model PR merged notification / Notify new model (push) Has been cancelled
PR CI / pr-ci (push) Has been cancelled
Slow tests on important models (on Push - A10) / Get all modified files (push) Has been cancelled
Secret Leaks / trufflehog (push) Has been cancelled
Update Transformers metadata / build_and_package (push) Has been cancelled
Slow tests on important models (on Push - A10) / Model CI (push) Has been cancelled
Check Tiny Models / Check tiny models (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Model CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Pipeline CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Example CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / DeepSpeed CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Trainer/FSDP CI (push) Has been cancelled
Nvidia CI - Flash Attn / Setup (push) Has been cancelled
Nvidia CI - Flash Attn / Model CI (push) Has been cancelled
Nvidia CI / Setup (push) Has been cancelled
Nvidia CI / Model CI (push) Has been cancelled
Nvidia CI / Torch pipeline CI (push) Has been cancelled
Nvidia CI / Example CI (push) Has been cancelled
Nvidia CI / Trainer/FSDP CI (push) Has been cancelled
Nvidia CI / DeepSpeed CI (push) Has been cancelled
Nvidia CI / Quantization CI (push) Has been cancelled
Nvidia CI / Kernels CI (push) Has been cancelled
Doctests / Setup (push) Has been cancelled
Doctests / Call doctest jobs (push) Has been cancelled
Doctests / Send results to webhook (push) Has been cancelled
Extras Smoke Test / Get supported Python versions (push) Has been cancelled
Extras Smoke Test / Test extras on Python ${{ matrix.python-version }} (push) Has been cancelled
Extras Smoke Test / Check Slack token availability (push) Has been cancelled
Extras Smoke Test / Notify failures to Slack (push) Has been cancelled
Self-hosted runner (AMD scheduled CI caller) / Trigger Scheduled AMD CI (push) Has been cancelled
Stale Bot / Close Stale Issues (push) Has been cancelled
18 lines
2.2 KiB
Python
18 lines
2.2 KiB
Python
import unittest
|
|
|
|
from transformers.models.camembert.tokenization_camembert import CamembertTokenizer
|
|
from transformers.testing_utils import require_tokenizers
|
|
|
|
from ...test_tokenization_common import TokenizerTesterMixin
|
|
|
|
|
|
@require_tokenizers
|
|
class CamembertTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
|
|
from_pretrained_id = ["almanach/camembert-base"]
|
|
tokenizer_class = CamembertTokenizer
|
|
|
|
integration_expected_tokens = ['▁This', '▁is', '▁a', '▁test', '▁', '😊', '▁I', '▁was', '▁', 'born', '▁in', '▁9', '2000', ',', '▁and', '▁this', '▁is', '▁fal', 'sé', '.', '▁', '生活的真谛是', '▁Hi', '▁Hello', '▁Hi', '▁Hello', '▁Hello', '<s>', '▁hi', '<s>', '▁the', 're', '▁The', '▁', 'follow', 'ing', '▁string', '▁s', 'h', 'ould', '▁be', '▁pro', 'per', 'ly', '▁en', 'code', 'd', ':', '▁Hello', '.', '▁But', '▁i', 'rd', '▁and', '▁', 'ปี', '▁i', 'rd', '▁', 'ด', '▁Hey', '▁h', 'ow', '▁are', '▁you', '▁do', 'ing'] # fmt: skip
|
|
integration_expected_token_ids = [17526, 2856, 33, 2006, 21, 3, 551, 15760, 21, 24900, 378, 419, 13233, 7, 1168, 9098, 2856, 19289, 5100, 9, 21, 3, 5108, 9774, 5108, 9774, 9774, 5, 7874, 5, 808, 346, 908, 21, 31189, 402, 20468, 52, 133, 19306, 2446, 909, 1399, 1107, 22, 14420, 204, 92, 9774, 9, 10503, 1723, 6682, 1168, 21, 3, 1723, 6682, 21, 3, 20128, 616, 3168, 9581, 4835, 7503, 402] # fmt: skip
|
|
expected_tokens_from_ids = ['▁This', '▁is', '▁a', '▁test', '▁', '<unk>', '▁I', '▁was', '▁', 'born', '▁in', '▁9', '2000', ',', '▁and', '▁this', '▁is', '▁fal', 'sé', '.', '▁', '<unk>', '▁Hi', '▁Hello', '▁Hi', '▁Hello', '▁Hello', '<s>', '▁hi', '<s>', '▁the', 're', '▁The', '▁', 'follow', 'ing', '▁string', '▁s', 'h', 'ould', '▁be', '▁pro', 'per', 'ly', '▁en', 'code', 'd', ':', '▁Hello', '.', '▁But', '▁i', 'rd', '▁and', '▁', '<unk>', '▁i', 'rd', '▁', '<unk>', '▁Hey', '▁h', 'ow', '▁are', '▁you', '▁do', 'ing'] # fmt: skip
|
|
integration_expected_decoded_text = "This is a test <unk> I was born in 92000, and this is falsé. <unk> Hi Hello Hi Hello Hello<s> hi<s> there The following string should be properly encoded: Hello. But ird and <unk> ird <unk> Hey how are you doing"
|