mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-05 13:50:13 +06:00
19420fd99e
* move test model folders (TODO: fix imports and others) * fix (potentially partially) imports (in model test modules) * fix (potentially partially) imports (in tokenization test modules) * fix (potentially partially) imports (in feature extraction test modules) * fix import utils.test_modeling_tf_core * fix path ../fixtures/ * fix imports about generation.test_generation_flax_utils * fix more imports * fix fixture path * fix get_test_dir * update module_to_test_file * fix get_tests_dir from wrong transformers.utils * update config.yml (CircleCI) * fix style * remove missing imports * update new model script * update check_repo * update SPECIAL_MODULE_TO_TEST_MAP * fix style * add __init__ * update self-scheduled * fix add_new_model scripts * check one way to get location back * python setup.py build install * fix import in test auto * update self-scheduled.yml * update slack notification script * Add comments about artifact names * fix for yolos Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
67 lines
2.6 KiB
Python
67 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.models.ctrl.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
|
|
test_seq2seq = 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)
|