wehub-resource-sync
194 lines
7.6 KiB
Python
194 lines
7.6 KiB
Python
# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
|
|
# Copyright 2020 The HuggingFace Team. All rights reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
import inspect
|
|
import tempfile
|
|
import unittest
|
|
|
|
from paddlenlp.transformers import SPIECE_UNDERLINE
|
|
from paddlenlp.transformers.mbart.modeling import shift_tokens_right
|
|
from paddlenlp.transformers.mbart.tokenizer import MBartTokenizer
|
|
|
|
from ...testing_utils import get_tests_dir
|
|
from ..test_tokenizer_common import TokenizerTesterMixin
|
|
|
|
SAMPLE_VOCAB = get_tests_dir("fixtures/test_sentencepiece.model")
|
|
|
|
EN_CODE = 250004
|
|
RO_CODE = 250026
|
|
|
|
|
|
class MBartTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
|
|
tokenizer_class = MBartTokenizer
|
|
test_sentencepiece = True
|
|
|
|
test_offsets = False
|
|
|
|
def setUp(self):
|
|
super().setUp()
|
|
|
|
# We have a SentencePiece fixture for testing
|
|
tokenizer = MBartTokenizer(SAMPLE_VOCAB, keep_accents=True)
|
|
tokenizer.save_pretrained(self.tmpdirname)
|
|
|
|
def test_full_tokenizer(self):
|
|
tokenizer = MBartTokenizer(SAMPLE_VOCAB, keep_accents=True)
|
|
|
|
tokens = tokenizer.tokenize("This is a test")
|
|
self.assertListEqual(tokens, ["▁This", "▁is", "▁a", "▁t", "est"])
|
|
|
|
self.assertListEqual(
|
|
tokenizer.convert_tokens_to_ids(tokens),
|
|
[value + tokenizer.fairseq_offset for value in [285, 46, 10, 170, 382]],
|
|
)
|
|
|
|
tokens = tokenizer.tokenize("I was born in 92000, and this is falsé.")
|
|
self.assertListEqual(
|
|
tokens,
|
|
[
|
|
SPIECE_UNDERLINE + "I",
|
|
SPIECE_UNDERLINE + "was",
|
|
SPIECE_UNDERLINE + "b",
|
|
"or",
|
|
"n",
|
|
SPIECE_UNDERLINE + "in",
|
|
SPIECE_UNDERLINE + "",
|
|
"9",
|
|
"2",
|
|
"0",
|
|
"0",
|
|
"0",
|
|
",",
|
|
SPIECE_UNDERLINE + "and",
|
|
SPIECE_UNDERLINE + "this",
|
|
SPIECE_UNDERLINE + "is",
|
|
SPIECE_UNDERLINE + "f",
|
|
"al",
|
|
"s",
|
|
"é",
|
|
".",
|
|
],
|
|
)
|
|
ids = tokenizer.convert_tokens_to_ids(tokens)
|
|
self.assertListEqual(
|
|
ids,
|
|
[
|
|
value + tokenizer.fairseq_offset
|
|
for value in [8, 21, 84, 55, 24, 19, 7, 2, 602, 347, 347, 347, 3, 12, 66, 46, 72, 80, 6, 2, 4]
|
|
# ^ unk: 2 + 1 = 3 unk: 2 + 1 = 3 ^
|
|
],
|
|
)
|
|
|
|
back_tokens = tokenizer.convert_ids_to_tokens(ids)
|
|
self.assertListEqual(
|
|
back_tokens,
|
|
[
|
|
SPIECE_UNDERLINE + "I",
|
|
SPIECE_UNDERLINE + "was",
|
|
SPIECE_UNDERLINE + "b",
|
|
"or",
|
|
"n",
|
|
SPIECE_UNDERLINE + "in",
|
|
SPIECE_UNDERLINE + "",
|
|
"<unk>",
|
|
"2",
|
|
"0",
|
|
"0",
|
|
"0",
|
|
",",
|
|
SPIECE_UNDERLINE + "and",
|
|
SPIECE_UNDERLINE + "this",
|
|
SPIECE_UNDERLINE + "is",
|
|
SPIECE_UNDERLINE + "f",
|
|
"al",
|
|
"s",
|
|
"<unk>",
|
|
".",
|
|
],
|
|
)
|
|
|
|
def test_tokenizer_slow_store_full_signature(self):
|
|
signature = inspect.signature(self.tokenizer_class.__init__)
|
|
tokenizer = self.get_tokenizer()
|
|
|
|
for parameter_name, parameter in signature.parameters.items():
|
|
if parameter.default != inspect.Parameter.empty:
|
|
if parameter_name != "mbart_type":
|
|
self.assertIn(parameter_name, tokenizer.init_kwargs)
|
|
|
|
|
|
class MBartEnroIntegrationTest(unittest.TestCase):
|
|
checkpoint_name = "mbart-large-en-ro"
|
|
src_text = [
|
|
" UN Chief Says There Is No Military Solution in Syria",
|
|
""" Secretary-General Ban Ki-moon says his response to Russia's stepped up military support for Syria is that "there is no military solution" to the nearly five-year conflict and more weapons will only worsen the violence and misery for millions of people.""",
|
|
]
|
|
tgt_text = [
|
|
"Şeful ONU declară că nu există o soluţie militară în Siria",
|
|
"Secretarul General Ban Ki-moon declară că răspunsul său la intensificarea sprijinului militar al Rusiei"
|
|
' pentru Siria este că "nu există o soluţie militară" la conflictul de aproape cinci ani şi că noi arme nu vor'
|
|
" face decât să înrăutăţească violenţele şi mizeria pentru milioane de oameni.",
|
|
]
|
|
expected_src_tokens = [8274, 127873, 25916, 7, 8622, 2071, 438, 67485, 53, 187895, 23, 51712, 2, EN_CODE]
|
|
|
|
@classmethod
|
|
def setUpClass(cls):
|
|
cls.tokenizer: MBartTokenizer = MBartTokenizer.from_pretrained(
|
|
cls.checkpoint_name, src_lang="en_XX", tgt_lang="ro_RO"
|
|
)
|
|
cls.pad_token_id = 1
|
|
return cls
|
|
|
|
def check_language_codes(self):
|
|
self.assertEqual(self.tokenizer.fairseq_tokens_to_ids["ar_AR"], 250001)
|
|
self.assertEqual(self.tokenizer.fairseq_tokens_to_ids["en_EN"], 250004)
|
|
self.assertEqual(self.tokenizer.fairseq_tokens_to_ids["ro_RO"], 250020)
|
|
|
|
def test_enro_tokenizer_decode_ignores_language_codes(self):
|
|
self.assertIn(RO_CODE, self.tokenizer.all_special_ids)
|
|
generated_ids = [RO_CODE, 884, 9019, 96, 9, 916, 86792, 36, 18743, 15596, 5, 2]
|
|
result = self.tokenizer.decode(generated_ids, skip_special_tokens=True)
|
|
expected_romanian = self.tokenizer.decode(generated_ids[1:], skip_special_tokens=True)
|
|
self.assertEqual(result, expected_romanian)
|
|
self.assertNotIn(self.tokenizer.eos_token, result)
|
|
|
|
def test_enro_tokenizer_truncation(self):
|
|
src_text = ["this is gunna be a long sentence " * 20]
|
|
assert isinstance(src_text[0], str)
|
|
desired_max_length = 10
|
|
ids = self.tokenizer(src_text, max_length=desired_max_length, truncation=True).input_ids[0]
|
|
self.assertEqual(ids[-2], 2)
|
|
self.assertEqual(ids[-1], EN_CODE)
|
|
self.assertEqual(len(ids), desired_max_length)
|
|
|
|
def test_mask_token(self):
|
|
self.assertListEqual(self.tokenizer.convert_tokens_to_ids(["<mask>", "ar_AR"]), [250026, 250001])
|
|
|
|
def test_special_tokens_unaffacted_by_save_load(self):
|
|
tmpdirname = tempfile.mkdtemp()
|
|
original_special_tokens = self.tokenizer.fairseq_tokens_to_ids
|
|
self.tokenizer.save_pretrained(tmpdirname)
|
|
new_tok = MBartTokenizer.from_pretrained(tmpdirname)
|
|
self.assertDictEqual(new_tok.fairseq_tokens_to_ids, original_special_tokens)
|
|
|
|
def test_seq2seq_max_length(self):
|
|
batch = self.tokenizer(self.src_text, padding=True, truncation=True, max_length=3, return_tensors="pd")
|
|
targets = self.tokenizer(self.tgt_text, padding=True, truncation=True, max_length=10, return_tensors="pd")
|
|
labels = targets["input_ids"]
|
|
batch["decoder_input_ids"] = shift_tokens_right(labels, self.tokenizer.pad_token_id)
|
|
|
|
self.assertEqual(batch.input_ids.shape[1], 3)
|
|
self.assertEqual(batch.decoder_input_ids.shape[1], 10)
|