mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-04 21:30:07 +06:00
ba8c4d0ac0
* splitting fast and slow tokenizers [WIP] * [WIP] splitting sentencepiece and tokenizers dependencies * update dummy objects * add name_or_path to models and tokenizers * prefix added to file names * prefix * styling + quality * spliting all the tokenizer files - sorting sentencepiece based ones * update tokenizer version up to 0.9.0 * remove hard dependency on sentencepiece 🎉 * and removed hard dependency on tokenizers 🎉 * update conversion script * update missing models * fixing tests * move test_tokenization_fast to main tokenization tests - fix bugs * bump up tokenizers * fix bert_generation * update ad fix several tokenizers * keep sentencepiece in deps for now * fix funnel and deberta tests * fix fsmt * fix marian tests * fix layoutlm * fix squeezebert and gpt2 * fix T5 tokenization * fix xlnet tests * style * fix mbart * bump up tokenizers to 0.9.2 * fix model tests * fix tf models * fix seq2seq examples * fix tests without sentencepiece * fix slow => fast conversion without sentencepiece * update auto and bert generation tests * fix mbart tests * fix auto and common test without tokenizers * fix tests without tokenizers * clean up tests lighten up when tokenizers + sentencepiece are both off * style quality and tests fixing * add sentencepiece to doc/examples reqs * leave sentencepiece on for now * style quality split hebert and fix pegasus * WIP Herbert fast * add sample_text_no_unicode and fix hebert tokenization * skip FSMT example test for now * fix style * fix fsmt in example tests * update following Lysandre and Sylvain's comments * Update src/transformers/testing_utils.py Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * Update src/transformers/testing_utils.py Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * Update src/transformers/tokenization_utils_base.py Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * Update src/transformers/tokenization_utils_base.py Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
105 lines
3.8 KiB
Python
105 lines
3.8 KiB
Python
# coding=utf-8
|
|
# Copyright 2019 Hugging Face inc.
|
|
#
|
|
# 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 os
|
|
import unittest
|
|
|
|
from transformers import AlbertTokenizer, AlbertTokenizerFast
|
|
from transformers.testing_utils import require_sentencepiece, require_tokenizers
|
|
|
|
from .test_tokenization_common import TokenizerTesterMixin
|
|
|
|
|
|
SAMPLE_VOCAB = os.path.join(os.path.dirname(os.path.abspath(__file__)), "fixtures/spiece.model")
|
|
|
|
|
|
@require_sentencepiece
|
|
@require_tokenizers
|
|
class AlbertTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
|
|
|
|
tokenizer_class = AlbertTokenizer
|
|
rust_tokenizer_class = AlbertTokenizerFast
|
|
test_rust_tokenizer = True
|
|
|
|
def setUp(self):
|
|
super().setUp()
|
|
|
|
# We have a SentencePiece fixture for testing
|
|
tokenizer = AlbertTokenizer(SAMPLE_VOCAB)
|
|
tokenizer.save_pretrained(self.tmpdirname)
|
|
|
|
def get_input_output_texts(self, tokenizer):
|
|
input_text = "this is a test"
|
|
output_text = "this is a test"
|
|
return input_text, output_text
|
|
|
|
def test_rust_and_python_full_tokenizers(self):
|
|
if not self.test_rust_tokenizer:
|
|
return
|
|
|
|
tokenizer = self.get_tokenizer()
|
|
rust_tokenizer = self.get_rust_tokenizer()
|
|
|
|
sequence = "I was born in 92000, and this is falsé."
|
|
|
|
tokens = tokenizer.tokenize(sequence)
|
|
rust_tokens = rust_tokenizer.tokenize(sequence)
|
|
self.assertListEqual(tokens, rust_tokens)
|
|
|
|
ids = tokenizer.encode(sequence, add_special_tokens=False)
|
|
rust_ids = rust_tokenizer.encode(sequence, add_special_tokens=False)
|
|
self.assertListEqual(ids, rust_ids)
|
|
|
|
rust_tokenizer = self.get_rust_tokenizer()
|
|
ids = tokenizer.encode(sequence)
|
|
rust_ids = rust_tokenizer.encode(sequence)
|
|
self.assertListEqual(ids, rust_ids)
|
|
|
|
def test_full_tokenizer(self):
|
|
tokenizer = AlbertTokenizer(SAMPLE_VOCAB, keep_accents=True)
|
|
|
|
tokens = tokenizer.tokenize("This is a test")
|
|
self.assertListEqual(tokens, ["▁this", "▁is", "▁a", "▁test"])
|
|
|
|
self.assertListEqual(tokenizer.convert_tokens_to_ids(tokens), [48, 25, 21, 1289])
|
|
|
|
tokens = tokenizer.tokenize("I was born in 92000, and this is falsé.")
|
|
self.assertListEqual(
|
|
tokens, ["▁i", "▁was", "▁born", "▁in", "▁9", "2000", ",", "▁and", "▁this", "▁is", "▁fal", "s", "é", "."]
|
|
)
|
|
ids = tokenizer.convert_tokens_to_ids(tokens)
|
|
self.assertListEqual(ids, [31, 23, 386, 19, 561, 3050, 15, 17, 48, 25, 8256, 18, 1, 9])
|
|
|
|
back_tokens = tokenizer.convert_ids_to_tokens(ids)
|
|
self.assertListEqual(
|
|
back_tokens,
|
|
["▁i", "▁was", "▁born", "▁in", "▁9", "2000", ",", "▁and", "▁this", "▁is", "▁fal", "s", "<unk>", "."],
|
|
)
|
|
|
|
def test_sequence_builders(self):
|
|
tokenizer = AlbertTokenizer(SAMPLE_VOCAB)
|
|
|
|
text = tokenizer.encode("sequence builders")
|
|
text_2 = tokenizer.encode("multi-sequence build")
|
|
|
|
encoded_sentence = tokenizer.build_inputs_with_special_tokens(text)
|
|
encoded_pair = tokenizer.build_inputs_with_special_tokens(text, text_2)
|
|
|
|
assert encoded_sentence == [tokenizer.cls_token_id] + text + [tokenizer.sep_token_id]
|
|
assert encoded_pair == [tokenizer.cls_token_id] + text + [tokenizer.sep_token_id] + text_2 + [
|
|
tokenizer.sep_token_id
|
|
]
|