mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-07 23:00:08 +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>
83 lines
2.6 KiB
Python
83 lines
2.6 KiB
Python
# coding=utf-8
|
|
# Copyright 2018 The Google AI Language Team Authors.
|
|
#
|
|
# 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 json
|
|
import os
|
|
import unittest
|
|
|
|
from transformers.tokenization_openai import VOCAB_FILES_NAMES, OpenAIGPTTokenizer, OpenAIGPTTokenizerFast
|
|
|
|
from .test_tokenization_common import TokenizerTesterMixin
|
|
|
|
|
|
class OpenAIGPTTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
|
|
|
|
tokenizer_class = OpenAIGPTTokenizer
|
|
rust_tokenizer_class = OpenAIGPTTokenizerFast
|
|
test_rust_tokenizer = True
|
|
|
|
def setUp(self):
|
|
super().setUp()
|
|
|
|
# Adapted from Sennrich et al. 2015 and https://github.com/rsennrich/subword-nmt
|
|
vocab = [
|
|
"l",
|
|
"o",
|
|
"w",
|
|
"e",
|
|
"r",
|
|
"s",
|
|
"t",
|
|
"i",
|
|
"d",
|
|
"n",
|
|
"w</w>",
|
|
"r</w>",
|
|
"t</w>",
|
|
"lo",
|
|
"low",
|
|
"er</w>",
|
|
"low</w>",
|
|
"lowest</w>",
|
|
"newer</w>",
|
|
"wider</w>",
|
|
"<unk>",
|
|
]
|
|
vocab_tokens = dict(zip(vocab, range(len(vocab))))
|
|
merges = ["#version: 0.2", "l o", "lo w", "e r</w>", ""]
|
|
|
|
self.vocab_file = os.path.join(self.tmpdirname, VOCAB_FILES_NAMES["vocab_file"])
|
|
self.merges_file = os.path.join(self.tmpdirname, VOCAB_FILES_NAMES["merges_file"])
|
|
with open(self.vocab_file, "w") as fp:
|
|
fp.write(json.dumps(vocab_tokens))
|
|
with open(self.merges_file, "w") as fp:
|
|
fp.write("\n".join(merges))
|
|
|
|
def get_input_output_texts(self, tokenizer):
|
|
return "lower newer", "lower newer"
|
|
|
|
def test_full_tokenizer(self):
|
|
tokenizer = OpenAIGPTTokenizer(self.vocab_file, self.merges_file)
|
|
|
|
text = "lower"
|
|
bpe_tokens = ["low", "er</w>"]
|
|
tokens = tokenizer.tokenize(text)
|
|
self.assertListEqual(tokens, bpe_tokens)
|
|
|
|
input_tokens = tokens + ["<unk>"]
|
|
input_bpe_tokens = [14, 15, 20]
|
|
self.assertListEqual(tokenizer.convert_tokens_to_ids(input_tokens), input_bpe_tokens)
|