mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-14 10:08:29 +06:00
9aeacb58ba
* [WIP] SP tokenizers * fixing tests for T5 * WIP tokenizers * serialization * update T5 * WIP T5 tokenization * slow to fast conversion script * Refactoring to move tokenzier implementations inside transformers * Adding gpt - refactoring - quality * WIP adding several tokenizers to the fast world * WIP Roberta - moving implementations * update to dev4 switch file loading to in-memory loading * Updating and fixing * advancing on the tokenizers - updating do_lower_case * style and quality * moving forward with tokenizers conversion and tests * MBart, T5 * dumping the fast version of transformer XL * Adding to autotokenizers + style/quality * update init and space_between_special_tokens * style and quality * bump up tokenizers version * add protobuf * fix pickle Bert JP with Mecab * fix newly added tokenizers * style and quality * fix bert japanese * fix funnel * limite tokenizer warning to one occurence * clean up file * fix new tokenizers * fast tokenizers deep tests * WIP adding all the special fast tests on the new fast tokenizers * quick fix * adding more fast tokenizers in the fast tests * all tokenizers in fast version tested * Adding BertGenerationFast * bump up setup.py for CI * remove BertGenerationFast (too early) * bump up tokenizers version * Clean old docstrings * Typo * Update following Lysandre comments Co-authored-by: Sylvain Gugger <sylvain.gugger@gmail.com>
80 lines
2.8 KiB
Python
80 lines
2.8 KiB
Python
# coding=utf-8
|
|
# Copyright 2020 HuggingFace Inc. team.
|
|
#
|
|
# 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.tokenization_funnel import VOCAB_FILES_NAMES, FunnelTokenizer, FunnelTokenizerFast
|
|
|
|
from .test_tokenization_common import TokenizerTesterMixin
|
|
|
|
|
|
class FunnelTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
|
|
|
|
tokenizer_class = FunnelTokenizer
|
|
test_rust_tokenizer = True
|
|
space_between_special_tokens = True
|
|
|
|
def setUp(self):
|
|
super().setUp()
|
|
|
|
vocab_tokens = [
|
|
"<unk>",
|
|
"<cls>",
|
|
"<sep>",
|
|
"want",
|
|
"##want",
|
|
"##ed",
|
|
"wa",
|
|
"un",
|
|
"runn",
|
|
"##ing",
|
|
",",
|
|
"low",
|
|
"lowest",
|
|
]
|
|
self.vocab_file = os.path.join(self.tmpdirname, VOCAB_FILES_NAMES["vocab_file"])
|
|
with open(self.vocab_file, "w", encoding="utf-8") as vocab_writer:
|
|
vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))
|
|
|
|
def get_tokenizer(self, **kwargs):
|
|
return FunnelTokenizer.from_pretrained(self.tmpdirname, **kwargs)
|
|
|
|
def get_rust_tokenizer(self, **kwargs):
|
|
return FunnelTokenizerFast.from_pretrained(self.tmpdirname, **kwargs)
|
|
|
|
def get_input_output_texts(self, tokenizer):
|
|
input_text = "UNwant\u00E9d,running"
|
|
output_text = "unwanted, running"
|
|
return input_text, output_text
|
|
|
|
def test_full_tokenizer(self):
|
|
tokenizer = self.tokenizer_class(self.vocab_file)
|
|
|
|
tokens = tokenizer.tokenize("UNwant\u00E9d,running")
|
|
self.assertListEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])
|
|
self.assertListEqual(tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
|
|
|
|
def test_token_type_ids(self):
|
|
tokenizers = self.get_tokenizers(do_lower_case=False)
|
|
for tokenizer in tokenizers:
|
|
inputs = tokenizer("UNwant\u00E9d,running")
|
|
sentence_len = len(inputs["input_ids"]) - 1
|
|
self.assertListEqual(inputs["token_type_ids"], [2] + [0] * sentence_len)
|
|
|
|
inputs = tokenizer("UNwant\u00E9d,running", "UNwant\u00E9d,running")
|
|
self.assertListEqual(inputs["token_type_ids"], [2] + [0] * sentence_len + [1] * sentence_len)
|