mirror of
https://github.com/mii443/tokenizers.git
synced 2025-08-23 16:49:27 +00:00
29fef1e7aa
* nits * Fixing deps. * Ruff update. * Import order matters. * Fix. * Revert ruff fix. * Visualizer. * Putting back the imports. --------- Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
99 lines
3.0 KiB
Python
99 lines
3.0 KiB
Python
from tokenizers import ByteLevelBPETokenizer
|
|
|
|
from ..utils import data_dir, multiprocessing_with_parallelism, roberta_files
|
|
|
|
|
|
class TestByteLevelBPE:
|
|
def test_basic_encode(self, roberta_files):
|
|
tokenizer = ByteLevelBPETokenizer.from_file(roberta_files["vocab"], roberta_files["merges"])
|
|
output = tokenizer.encode("The quick brown fox jumps over the lazy dog")
|
|
|
|
assert output.ids == [133, 2119, 6219, 23602, 13855, 81, 5, 22414, 2335]
|
|
assert output.tokens == [
|
|
"The",
|
|
"Ġquick",
|
|
"Ġbrown",
|
|
"Ġfox",
|
|
"Ġjumps",
|
|
"Ġover",
|
|
"Ġthe",
|
|
"Ġlazy",
|
|
"Ġdog",
|
|
]
|
|
assert output.offsets == [
|
|
(0, 3),
|
|
(3, 9),
|
|
(9, 15),
|
|
(15, 19),
|
|
(19, 25),
|
|
(25, 30),
|
|
(30, 34),
|
|
(34, 39),
|
|
(39, 43),
|
|
]
|
|
|
|
def test_add_prefix_space(self, roberta_files):
|
|
tokenizer = ByteLevelBPETokenizer.from_file(
|
|
roberta_files["vocab"], roberta_files["merges"], add_prefix_space=True
|
|
)
|
|
output = tokenizer.encode("The quick brown fox jumps over the lazy dog")
|
|
|
|
assert output.ids == [20, 2119, 6219, 23602, 13855, 81, 5, 22414, 2335]
|
|
assert output.tokens == [
|
|
"ĠThe",
|
|
"Ġquick",
|
|
"Ġbrown",
|
|
"Ġfox",
|
|
"Ġjumps",
|
|
"Ġover",
|
|
"Ġthe",
|
|
"Ġlazy",
|
|
"Ġdog",
|
|
]
|
|
assert output.offsets == [
|
|
(0, 3),
|
|
(3, 9),
|
|
(9, 15),
|
|
(15, 19),
|
|
(19, 25),
|
|
(25, 30),
|
|
(30, 34),
|
|
(34, 39),
|
|
(39, 43),
|
|
]
|
|
|
|
def test_lowerspace(self, roberta_files):
|
|
tokenizer = ByteLevelBPETokenizer.from_file(
|
|
roberta_files["vocab"],
|
|
roberta_files["merges"],
|
|
add_prefix_space=True,
|
|
lowercase=True,
|
|
)
|
|
output = tokenizer.encode("The Quick Brown Fox Jumps Over The Lazy Dog")
|
|
|
|
assert output.ids == [5, 2119, 6219, 23602, 13855, 81, 5, 22414, 2335]
|
|
assert output.tokens == [
|
|
"Ġthe",
|
|
"Ġquick",
|
|
"Ġbrown",
|
|
"Ġfox",
|
|
"Ġjumps",
|
|
"Ġover",
|
|
"Ġthe",
|
|
"Ġlazy",
|
|
"Ġdog",
|
|
]
|
|
|
|
def test_multiprocessing_with_parallelism(self, roberta_files):
|
|
tokenizer = ByteLevelBPETokenizer.from_file(roberta_files["vocab"], roberta_files["merges"])
|
|
multiprocessing_with_parallelism(tokenizer, False)
|
|
multiprocessing_with_parallelism(tokenizer, True)
|
|
|
|
def test_train_from_iterator(self):
|
|
text = ["A first sentence", "Another sentence", "And a last one"]
|
|
tokenizer = ByteLevelBPETokenizer()
|
|
tokenizer.train_from_iterator(text, show_progress=False)
|
|
|
|
output = tokenizer.encode("A sentence")
|
|
assert output.tokens == ["A", "Ġsentence"]
|