mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-03 12:50:06 +06:00
f9414f7553
* Better None gradients handling * Apply Style * Apply Style * Create a loss class per task to compute its respective loss * Add loss classes to the ALBERT TF models * Add loss classes to the BERT TF models * Add question answering and multiple choice to TF Camembert * Remove prints * Add multiple choice model to TF DistilBERT + loss computation * Add question answering model to TF Electra + loss computation * Add token classification, question answering and multiple choice models to TF Flaubert * Add multiple choice model to TF Roberta + loss computation * Add multiple choice model to TF XLM + loss computation * Add multiple choice and question answering models to TF XLM-Roberta * Add multiple choice model to TF XLNet + loss computation * Remove unused parameters * Add task loss classes * Reorder TF imports + add new model classes * Add new model classes * Bugfix in TF T5 model * Bugfix for TF T5 tests * Bugfix in TF T5 model * Fix TF T5 model tests * Fix T5 tests + some renaming * Fix inheritance issue in the AutoX tests * Add tests for TF Flaubert and TF XLM Roberta * Add tests for TF Flaubert and TF XLM Roberta * Remove unused piece of code in the TF trainer * bugfix and remove unused code * Bugfix for TF 2.2 * Apply Style * Divide TFSequenceClassificationAndMultipleChoiceLoss into their two respective name * Apply style * Mirror the PT Trainer in the TF one: fp16, optimizers and tb_writer as class parameter and better dataset handling * Fix TF optimizations tests and apply style * Remove useless parameter * Bugfix and apply style * Fix TF Trainer prediction * Now the TF models return the loss such as their PyTorch couterparts * Apply Style * Ignore some tests output * Take into account the SQuAD cls_index, p_mask and is_impossible parameters for the QuestionAnswering task models. * Fix names for SQuAD data * Apply Style * Fix conflicts with 2.11 release * Fix conflicts with 2.11 * Fix wrongname * Add better documentation on the new create_optimizer function * Fix isort * logging_dir: use same default as PyTorch Co-authored-by: Julien Chaumond <chaumond@gmail.com>
56 lines
1.9 KiB
Python
56 lines
1.9 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 .utils import require_tf, slow
|
|
|
|
|
|
if is_tf_available():
|
|
import tensorflow as tf
|
|
import numpy as np
|
|
from transformers import TFXLMRobertaModel
|
|
|
|
|
|
@require_tf
|
|
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)[0]
|
|
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))
|