mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-04 13:20:12 +06:00
476ba679dd
* feature for tokenizer without slow/legacy version * format * modify common test * add tests * add PreTrainedTokenizerFast to AutoTokenizer * format * change tokenizer common test in order to be able to run test without a slow version * update tokenizer fast test in order to use `rust_tokenizer_class` attribute instead of `tokenizer_class` * add autokenizer test * replace `if self.tokenizer_class is not None` with ` if self.tokenizer_class is None` * remove obsolete change in comment * Update src/transformers/tokenization_utils_base.py Co-authored-by: Lysandre Debut <lysandre@huggingface.co> * Update src/transformers/tokenization_utils_fast.py Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * change `get_main_tokenizer` into `get_tokenizers` * clarify `get_tokenizers` method * homogenize with `test_slow_tokenizer` and `test_rust_tokenizer` * add `test_rust_tokenizer = False` to tokenizer which don't define a fast version * `test_rust_tokenizer = False` for BertJapaneseTokenizer * `test_rust_tokenizer = False` for BertJapaneseCharacterTokenizationTest Co-authored-by: Lysandre Debut <lysandre@huggingface.co> Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
88 lines
3.5 KiB
Python
88 lines
3.5 KiB
Python
#!/usr/bin/env python3
|
|
# coding=utf-8
|
|
# 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.
|
|
"""Tests for the Blenderbot small tokenizer."""
|
|
import json
|
|
import os
|
|
import unittest
|
|
|
|
from transformers.models.blenderbot_small.tokenization_blenderbot_small import (
|
|
VOCAB_FILES_NAMES,
|
|
BlenderbotSmallTokenizer,
|
|
)
|
|
|
|
from .test_tokenization_common import TokenizerTesterMixin
|
|
|
|
|
|
class BlenderbotSmallTokenizerTest(TokenizerTesterMixin, unittest.TestCase):
|
|
|
|
tokenizer_class = BlenderbotSmallTokenizer
|
|
test_rust_tokenizer = False
|
|
|
|
def setUp(self):
|
|
super().setUp()
|
|
|
|
vocab = ["__start__", "adapt", "act", "ap@@", "te", "__end__", "__unk__"]
|
|
vocab_tokens = dict(zip(vocab, range(len(vocab))))
|
|
|
|
merges = ["#version: 0.2", "a p", "t e</w>", "ap t</w>", "a d", "ad apt</w>", "a c", "ac t</w>", ""]
|
|
self.special_tokens_map = {"unk_token": "__unk__", "bos_token": "__start__", "eos_token": "__end__"}
|
|
|
|
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 BlenderbotSmallTokenizer.from_pretrained(self.tmpdirname, **kwargs)
|
|
|
|
def get_input_output_texts(self, tokenizer):
|
|
input_text = "adapt act apte"
|
|
output_text = "adapt act apte"
|
|
return input_text, output_text
|
|
|
|
def test_full_blenderbot_small_tokenizer(self):
|
|
tokenizer = BlenderbotSmallTokenizer(self.vocab_file, self.merges_file, **self.special_tokens_map)
|
|
text = "adapt act apte"
|
|
bpe_tokens = ["adapt", "act", "ap@@", "te"]
|
|
tokens = tokenizer.tokenize(text)
|
|
self.assertListEqual(tokens, bpe_tokens)
|
|
|
|
input_tokens = [tokenizer.bos_token] + tokens + [tokenizer.eos_token]
|
|
|
|
input_bpe_tokens = [0, 1, 2, 3, 4, 5]
|
|
self.assertListEqual(tokenizer.convert_tokens_to_ids(input_tokens), input_bpe_tokens)
|
|
|
|
def test_special_tokens_small_tok(self):
|
|
tok = BlenderbotSmallTokenizer.from_pretrained("facebook/blenderbot-90M")
|
|
assert tok("sam").input_ids == [1384]
|
|
src_text = "I am a small frog."
|
|
encoded = tok([src_text], padding=False, truncation=False)["input_ids"]
|
|
decoded = tok.batch_decode(encoded, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
|
|
assert src_text != decoded # I wish it did!
|
|
assert decoded == "i am a small frog ."
|
|
|
|
def test_empty_word_small_tok(self):
|
|
tok = BlenderbotSmallTokenizer.from_pretrained("facebook/blenderbot-90M")
|
|
src_text = "I am a small frog ."
|
|
src_text_dot = "."
|
|
encoded = tok(src_text)["input_ids"]
|
|
encoded_dot = tok(src_text_dot)["input_ids"]
|
|
|
|
assert encoded[-1] == encoded_dot[0]
|