wehub-resource-sync
e06fe8e8c6
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
Self-hosted runner (benchmark) / Benchmark (aws-g5-4xlarge-cache) (push) Has been cancelled
New model PR merged notification / Notify new model (push) Has been cancelled
Update Transformers metadata / build_and_package (push) Has been cancelled
19 lines
2.6 KiB
Python
19 lines
2.6 KiB
Python
import unittest
|
||
|
||
from tests.test_tokenization_common import TokenizerTesterMixin
|
||
from transformers.models.codegen.tokenization_codegen import CodeGenTokenizer
|
||
from transformers.testing_utils import (
|
||
require_tokenizers,
|
||
)
|
||
|
||
|
||
@require_tokenizers
|
||
class CodeGenTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
|
||
from_pretrained_id = ["Salesforce/codegen-350M-mono"]
|
||
tokenizer_class = CodeGenTokenizer
|
||
|
||
integration_expected_tokens = ['This', 'Ġis', 'Ġa', 'Ġtest', 'ĠðŁĺ', 'Ĭ', 'Ċ', 'I', 'Ġwas', 'Ġborn', 'Ġin', 'Ġ92', '000', ',', 'Ġand', 'Ġthis', 'Ġis', 'Ġfals', 'é', '.', 'Ċ', 'çĶŁ', 'æ', '´', '»', 'çļĦ', 'çľ', 'Ł', 'è', '°', 'Ľ', 'æĺ¯', 'Ċ', 'Hi', ' ', 'Hello', 'Ċ', 'Hi', ' ', 'Hello', 'ĊĊ', 'Ġ', 'Ċ', ' ', 'Ċ', 'ĠHello', 'Ċ', '<', 's', '>', 'Ċ', 'hi', '<', 's', '>', 'there', 'Ċ', 'The', 'Ġfollowing', 'Ġstring', 'Ġshould', 'Ġbe', 'Ġproperly', 'Ġencoded', ':', 'ĠHello', '.', 'Ċ', 'But', 'Ġ', 'ird', 'Ġand', 'Ġ', 'à¸', 'Ľ', 'à¸', 'µ', ' ', 'ird', ' ', 'à¸', 'Ķ', 'Ċ', 'Hey', 'Ġhow', 'Ġare', 'Ġyou', 'Ġdoing'] # fmt: skip
|
||
integration_expected_token_ids = [1212, 318, 257, 1332, 30325, 232, 198, 40, 373, 4642, 287, 10190, 830, 11, 290, 428, 318, 27807, 2634, 13, 198, 37955, 162, 112, 119, 21410, 40367, 253, 164, 108, 249, 42468, 198, 17250, 50286, 15496, 198, 17250, 50285, 15496, 628, 220, 198, 50286, 198, 18435, 198, 27, 82, 29, 198, 5303, 27, 82, 29, 8117, 198, 464, 1708, 4731, 815, 307, 6105, 30240, 25, 18435, 13, 198, 1537, 220, 1447, 290, 220, 19567, 249, 19567, 113, 50285, 1447, 50285, 19567, 242, 198, 10814, 703, 389, 345, 1804] # fmt: skip
|
||
expected_tokens_from_ids = ['This', 'Ġis', 'Ġa', 'Ġtest', 'ĠðŁĺ', 'Ĭ', 'Ċ', 'I', 'Ġwas', 'Ġborn', 'Ġin', 'Ġ92', '000', ',', 'Ġand', 'Ġthis', 'Ġis', 'Ġfals', 'é', '.', 'Ċ', 'çĶŁ', 'æ', '´', '»', 'çļĦ', 'çľ', 'Ł', 'è', '°', 'Ľ', 'æĺ¯', 'Ċ', 'Hi', ' ', 'Hello', 'Ċ', 'Hi', ' ', 'Hello', 'ĊĊ', 'Ġ', 'Ċ', ' ', 'Ċ', 'ĠHello', 'Ċ', '<', 's', '>', 'Ċ', 'hi', '<', 's', '>', 'there', 'Ċ', 'The', 'Ġfollowing', 'Ġstring', 'Ġshould', 'Ġbe', 'Ġproperly', 'Ġencoded', ':', 'ĠHello', '.', 'Ċ', 'But', 'Ġ', 'ird', 'Ġand', 'Ġ', 'à¸', 'Ľ', 'à¸', 'µ', ' ', 'ird', ' ', 'à¸', 'Ķ', 'Ċ', 'Hey', 'Ġhow', 'Ġare', 'Ġyou', 'Ġdoing'] # fmt: skip
|
||
integration_expected_decoded_text = "This is a test 😊\nI was born in 92000, and this is falsé.\n生活的真谛是\nHi Hello\nHi Hello\n\n \n \n Hello\n<s>\nhi<s>there\nThe following string should be properly encoded: Hello.\nBut ird and ปี ird ด\nHey how are you doing"
|