mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-07 23:00:08 +06:00
ba8c4d0ac0
* splitting fast and slow tokenizers [WIP] * [WIP] splitting sentencepiece and tokenizers dependencies * update dummy objects * add name_or_path to models and tokenizers * prefix added to file names * prefix * styling + quality * spliting all the tokenizer files - sorting sentencepiece based ones * update tokenizer version up to 0.9.0 * remove hard dependency on sentencepiece 🎉 * and removed hard dependency on tokenizers 🎉 * update conversion script * update missing models * fixing tests * move test_tokenization_fast to main tokenization tests - fix bugs * bump up tokenizers * fix bert_generation * update ad fix several tokenizers * keep sentencepiece in deps for now * fix funnel and deberta tests * fix fsmt * fix marian tests * fix layoutlm * fix squeezebert and gpt2 * fix T5 tokenization * fix xlnet tests * style * fix mbart * bump up tokenizers to 0.9.2 * fix model tests * fix tf models * fix seq2seq examples * fix tests without sentencepiece * fix slow => fast conversion without sentencepiece * update auto and bert generation tests * fix mbart tests * fix auto and common test without tokenizers * fix tests without tokenizers * clean up tests lighten up when tokenizers + sentencepiece are both off * style quality and tests fixing * add sentencepiece to doc/examples reqs * leave sentencepiece on for now * style quality split hebert and fix pegasus * WIP Herbert fast * add sample_text_no_unicode and fix hebert tokenization * skip FSMT example test for now * fix style * fix fsmt in example tests * update following Lysandre and Sylvain's comments * Update src/transformers/testing_utils.py Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * Update src/transformers/testing_utils.py Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * Update src/transformers/tokenization_utils_base.py Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * Update src/transformers/tokenization_utils_base.py Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
58 lines
2.0 KiB
Python
58 lines
2.0 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 unittest
|
|
|
|
from transformers import is_tf_available
|
|
from transformers.testing_utils import require_sentencepiece, require_tf, require_tokenizers, slow
|
|
|
|
|
|
if is_tf_available():
|
|
import numpy as np
|
|
import tensorflow as tf
|
|
|
|
from transformers import TFXLMRobertaModel
|
|
|
|
|
|
@require_tf
|
|
@require_sentencepiece
|
|
@require_tokenizers
|
|
class TFFlaubertModelIntegrationTest(unittest.TestCase):
|
|
@slow
|
|
def test_output_embeds_base_model(self):
|
|
model = TFXLMRobertaModel.from_pretrained("jplu/tf-xlm-roberta-base")
|
|
|
|
features = {
|
|
"input_ids": tf.convert_to_tensor([[0, 2646, 10269, 83, 99942, 2]], dtype=tf.int32), # "My dog is cute"
|
|
"attention_mask": tf.convert_to_tensor([[1, 1, 1, 1, 1, 1]], dtype=tf.int32),
|
|
}
|
|
|
|
output = model(features)["last_hidden_state"]
|
|
expected_shape = tf.TensorShape((1, 6, 768))
|
|
self.assertEqual(output.shape, expected_shape)
|
|
# compare the actual values for a slice.
|
|
expected_slice = tf.convert_to_tensor(
|
|
[
|
|
[
|
|
[0.0681762, 0.10894451, 0.06772504],
|
|
[-0.06423668, 0.02366615, 0.04329344],
|
|
[-0.06057295, 0.09974135, -0.00070584],
|
|
]
|
|
],
|
|
dtype=tf.float32,
|
|
)
|
|
|
|
self.assertTrue(np.allclose(output[:, :3, :3].numpy(), expected_slice.numpy(), atol=1e-4))
|