mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-06 14:20:04 +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>
66 lines
2.6 KiB
Python
66 lines
2.6 KiB
Python
# coding=utf-8
|
|
# Copyright 2018 Salesforce and 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 json
|
|
import os
|
|
import unittest
|
|
|
|
from transformers.tokenization_ctrl import VOCAB_FILES_NAMES, CTRLTokenizer
|
|
|
|
from .test_tokenization_common import TokenizerTesterMixin
|
|
|
|
|
|
class CTRLTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
|
|
|
|
tokenizer_class = CTRLTokenizer
|
|
test_rust_tokenizer = False
|
|
|
|
def setUp(self):
|
|
super().setUp()
|
|
|
|
# Adapted from Sennrich et al. 2015 and https://github.com/rsennrich/subword-nmt
|
|
vocab = ["adapt", "re@@", "a@@", "apt", "c@@", "t", "<unk>"]
|
|
vocab_tokens = dict(zip(vocab, range(len(vocab))))
|
|
merges = ["#version: 0.2", "a p", "ap t</w>", "r e", "a d", "ad apt</w>", ""]
|
|
self.special_tokens_map = {"unk_token": "<unk>"}
|
|
|
|
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", encoding="utf-8") as fp:
|
|
fp.write(json.dumps(vocab_tokens) + "\n")
|
|
with open(self.merges_file, "w", encoding="utf-8") as fp:
|
|
fp.write("\n".join(merges))
|
|
|
|
def get_tokenizer(self, **kwargs):
|
|
kwargs.update(self.special_tokens_map)
|
|
return CTRLTokenizer.from_pretrained(self.tmpdirname, **kwargs)
|
|
|
|
def get_input_output_texts(self, tokenizer):
|
|
input_text = "adapt react readapt apt"
|
|
output_text = "adapt react readapt apt"
|
|
return input_text, output_text
|
|
|
|
def test_full_tokenizer(self):
|
|
tokenizer = CTRLTokenizer(self.vocab_file, self.merges_file, **self.special_tokens_map)
|
|
text = "adapt react readapt apt"
|
|
bpe_tokens = "adapt re@@ a@@ c@@ t re@@ adapt apt".split()
|
|
tokens = tokenizer.tokenize(text)
|
|
self.assertListEqual(tokens, bpe_tokens)
|
|
|
|
input_tokens = tokens + [tokenizer.unk_token]
|
|
|
|
input_bpe_tokens = [0, 1, 2, 4, 5, 1, 0, 3, 6]
|
|
self.assertListEqual(tokenizer.convert_tokens_to_ids(input_tokens), input_bpe_tokens)
|