mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-05 05:40:05 +06:00
5bf9afbf35
* Refactor tensor creation in tokenizers.
* Make sure to convert string to TensorType
* Refactor convert_to_tensors_
* Introduce numpy tensor creation
* Format
* Add unittest for TensorType creation from str
* sorting imports
* Added unittests for numpy tensor conversion.
* Do not use in-place version for squeeze as numpy doesn't provide such feature.
* Added extra parameter prepend_batch_axis: bool on prepare_for_model.
* Ensure test_np_encode_plus_sent_to_model is not executed if encoder/decoder model.
* style.
* numpy tests require_torch for now while flax not merged.
* Hopefully will make flake8 happy.
* One more time 🎶
47 lines
1.8 KiB
Python
47 lines
1.8 KiB
Python
# coding=utf-8
|
|
# Copyright 2018 HuggingFace Inc..
|
|
#
|
|
# 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 unittest
|
|
|
|
from transformers import PreTrainedTokenizer, TensorType
|
|
from transformers.tokenization_gpt2 import GPT2Tokenizer
|
|
|
|
from .utils import slow
|
|
|
|
|
|
class TokenizerUtilsTest(unittest.TestCase):
|
|
def check_tokenizer_from_pretrained(self, tokenizer_class):
|
|
s3_models = list(tokenizer_class.max_model_input_sizes.keys())
|
|
for model_name in s3_models[:1]:
|
|
tokenizer = tokenizer_class.from_pretrained(model_name)
|
|
self.assertIsNotNone(tokenizer)
|
|
self.assertIsInstance(tokenizer, tokenizer_class)
|
|
self.assertIsInstance(tokenizer, PreTrainedTokenizer)
|
|
|
|
for special_tok in tokenizer.all_special_tokens:
|
|
self.assertIsInstance(special_tok, str)
|
|
special_tok_id = tokenizer.convert_tokens_to_ids(special_tok)
|
|
self.assertIsInstance(special_tok_id, int)
|
|
|
|
@slow
|
|
def test_pretrained_tokenizers(self):
|
|
self.check_tokenizer_from_pretrained(GPT2Tokenizer)
|
|
|
|
def check_tensor_type_from_str(self):
|
|
self.assertEqual(TensorType("tf"), TensorType.TENSORFLOW)
|
|
self.assertEqual(TensorType("pt"), TensorType.PYTORCH)
|
|
self.assertEqual(TensorType("np"), TensorType.NUMPY)
|