Move test model folders (#17034)
* 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>
This commit is contained in:
Yih-Dar
0
tests/models/albert/__init__.py
Normal file
0
tests/models/albert/__init__.py
Normal file
309
tests/models/albert/test_modeling_albert.py
Normal file
309
tests/models/albert/test_modeling_albert.py
Normal file
@@ -0,0 +1,309 @@
|
||||
# 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.
|
||||
|
||||
|
||||
import unittest
|
||||
|
||||
from transformers import AlbertConfig, is_torch_available
|
||||
from transformers.models.auto import get_values
|
||||
from transformers.testing_utils import require_torch, slow, torch_device
|
||||
|
||||
from ...test_configuration_common import ConfigTester
|
||||
from ...test_modeling_common import ModelTesterMixin, ids_tensor, random_attention_mask
|
||||
|
||||
|
||||
if is_torch_available():
|
||||
import torch
|
||||
|
||||
from transformers import (
|
||||
MODEL_FOR_PRETRAINING_MAPPING,
|
||||
AlbertForMaskedLM,
|
||||
AlbertForMultipleChoice,
|
||||
AlbertForPreTraining,
|
||||
AlbertForQuestionAnswering,
|
||||
AlbertForSequenceClassification,
|
||||
AlbertForTokenClassification,
|
||||
AlbertModel,
|
||||
)
|
||||
from transformers.models.albert.modeling_albert import ALBERT_PRETRAINED_MODEL_ARCHIVE_LIST
|
||||
|
||||
|
||||
class AlbertModelTester:
|
||||
def __init__(
|
||||
self,
|
||||
parent,
|
||||
):
|
||||
self.parent = parent
|
||||
self.batch_size = 13
|
||||
self.seq_length = 7
|
||||
self.is_training = True
|
||||
self.use_input_mask = True
|
||||
self.use_token_type_ids = True
|
||||
self.use_labels = True
|
||||
self.vocab_size = 99
|
||||
self.embedding_size = 16
|
||||
self.hidden_size = 36
|
||||
self.num_hidden_layers = 6
|
||||
self.num_hidden_groups = 6
|
||||
self.num_attention_heads = 6
|
||||
self.intermediate_size = 37
|
||||
self.hidden_act = "gelu"
|
||||
self.hidden_dropout_prob = 0.1
|
||||
self.attention_probs_dropout_prob = 0.1
|
||||
self.max_position_embeddings = 512
|
||||
self.type_vocab_size = 16
|
||||
self.type_sequence_label_size = 2
|
||||
self.initializer_range = 0.02
|
||||
self.num_labels = 3
|
||||
self.num_choices = 4
|
||||
self.scope = None
|
||||
|
||||
def prepare_config_and_inputs(self):
|
||||
input_ids = ids_tensor([self.batch_size, self.seq_length], self.vocab_size)
|
||||
|
||||
input_mask = None
|
||||
if self.use_input_mask:
|
||||
input_mask = random_attention_mask([self.batch_size, self.seq_length])
|
||||
|
||||
token_type_ids = None
|
||||
if self.use_token_type_ids:
|
||||
token_type_ids = ids_tensor([self.batch_size, self.seq_length], self.type_vocab_size)
|
||||
|
||||
sequence_labels = None
|
||||
token_labels = None
|
||||
choice_labels = None
|
||||
if self.use_labels:
|
||||
sequence_labels = ids_tensor([self.batch_size], self.type_sequence_label_size)
|
||||
token_labels = ids_tensor([self.batch_size, self.seq_length], self.num_labels)
|
||||
choice_labels = ids_tensor([self.batch_size], self.num_choices)
|
||||
|
||||
config = self.get_config()
|
||||
|
||||
return config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
|
||||
def get_config(self):
|
||||
return AlbertConfig(
|
||||
vocab_size=self.vocab_size,
|
||||
hidden_size=self.hidden_size,
|
||||
num_hidden_layers=self.num_hidden_layers,
|
||||
num_attention_heads=self.num_attention_heads,
|
||||
intermediate_size=self.intermediate_size,
|
||||
hidden_act=self.hidden_act,
|
||||
hidden_dropout_prob=self.hidden_dropout_prob,
|
||||
attention_probs_dropout_prob=self.attention_probs_dropout_prob,
|
||||
max_position_embeddings=self.max_position_embeddings,
|
||||
type_vocab_size=self.type_vocab_size,
|
||||
initializer_range=self.initializer_range,
|
||||
num_hidden_groups=self.num_hidden_groups,
|
||||
)
|
||||
|
||||
def create_and_check_model(
|
||||
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
):
|
||||
model = AlbertModel(config=config)
|
||||
model.to(torch_device)
|
||||
model.eval()
|
||||
result = model(input_ids, attention_mask=input_mask, token_type_ids=token_type_ids)
|
||||
result = model(input_ids, token_type_ids=token_type_ids)
|
||||
result = model(input_ids)
|
||||
self.parent.assertEqual(result.last_hidden_state.shape, (self.batch_size, self.seq_length, self.hidden_size))
|
||||
self.parent.assertEqual(result.pooler_output.shape, (self.batch_size, self.hidden_size))
|
||||
|
||||
def create_and_check_for_pretraining(
|
||||
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
):
|
||||
model = AlbertForPreTraining(config=config)
|
||||
model.to(torch_device)
|
||||
model.eval()
|
||||
result = model(
|
||||
input_ids,
|
||||
attention_mask=input_mask,
|
||||
token_type_ids=token_type_ids,
|
||||
labels=token_labels,
|
||||
sentence_order_label=sequence_labels,
|
||||
)
|
||||
self.parent.assertEqual(result.prediction_logits.shape, (self.batch_size, self.seq_length, self.vocab_size))
|
||||
self.parent.assertEqual(result.sop_logits.shape, (self.batch_size, config.num_labels))
|
||||
|
||||
def create_and_check_for_masked_lm(
|
||||
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
):
|
||||
model = AlbertForMaskedLM(config=config)
|
||||
model.to(torch_device)
|
||||
model.eval()
|
||||
result = model(input_ids, attention_mask=input_mask, token_type_ids=token_type_ids, labels=token_labels)
|
||||
self.parent.assertEqual(result.logits.shape, (self.batch_size, self.seq_length, self.vocab_size))
|
||||
|
||||
def create_and_check_for_question_answering(
|
||||
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
):
|
||||
model = AlbertForQuestionAnswering(config=config)
|
||||
model.to(torch_device)
|
||||
model.eval()
|
||||
result = model(
|
||||
input_ids,
|
||||
attention_mask=input_mask,
|
||||
token_type_ids=token_type_ids,
|
||||
start_positions=sequence_labels,
|
||||
end_positions=sequence_labels,
|
||||
)
|
||||
self.parent.assertEqual(result.start_logits.shape, (self.batch_size, self.seq_length))
|
||||
self.parent.assertEqual(result.end_logits.shape, (self.batch_size, self.seq_length))
|
||||
|
||||
def create_and_check_for_sequence_classification(
|
||||
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
):
|
||||
config.num_labels = self.num_labels
|
||||
model = AlbertForSequenceClassification(config)
|
||||
model.to(torch_device)
|
||||
model.eval()
|
||||
result = model(input_ids, attention_mask=input_mask, token_type_ids=token_type_ids, labels=sequence_labels)
|
||||
self.parent.assertEqual(result.logits.shape, (self.batch_size, self.num_labels))
|
||||
|
||||
def create_and_check_for_token_classification(
|
||||
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
):
|
||||
config.num_labels = self.num_labels
|
||||
model = AlbertForTokenClassification(config=config)
|
||||
model.to(torch_device)
|
||||
model.eval()
|
||||
result = model(input_ids, attention_mask=input_mask, token_type_ids=token_type_ids, labels=token_labels)
|
||||
self.parent.assertEqual(result.logits.shape, (self.batch_size, self.seq_length, self.num_labels))
|
||||
|
||||
def create_and_check_for_multiple_choice(
|
||||
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
):
|
||||
config.num_choices = self.num_choices
|
||||
model = AlbertForMultipleChoice(config=config)
|
||||
model.to(torch_device)
|
||||
model.eval()
|
||||
multiple_choice_inputs_ids = input_ids.unsqueeze(1).expand(-1, self.num_choices, -1).contiguous()
|
||||
multiple_choice_token_type_ids = token_type_ids.unsqueeze(1).expand(-1, self.num_choices, -1).contiguous()
|
||||
multiple_choice_input_mask = input_mask.unsqueeze(1).expand(-1, self.num_choices, -1).contiguous()
|
||||
result = model(
|
||||
multiple_choice_inputs_ids,
|
||||
attention_mask=multiple_choice_input_mask,
|
||||
token_type_ids=multiple_choice_token_type_ids,
|
||||
labels=choice_labels,
|
||||
)
|
||||
self.parent.assertEqual(result.logits.shape, (self.batch_size, self.num_choices))
|
||||
|
||||
def prepare_config_and_inputs_for_common(self):
|
||||
config_and_inputs = self.prepare_config_and_inputs()
|
||||
(
|
||||
config,
|
||||
input_ids,
|
||||
token_type_ids,
|
||||
input_mask,
|
||||
sequence_labels,
|
||||
token_labels,
|
||||
choice_labels,
|
||||
) = config_and_inputs
|
||||
inputs_dict = {"input_ids": input_ids, "token_type_ids": token_type_ids, "attention_mask": input_mask}
|
||||
return config, inputs_dict
|
||||
|
||||
|
||||
@require_torch
|
||||
class AlbertModelTest(ModelTesterMixin, unittest.TestCase):
|
||||
|
||||
all_model_classes = (
|
||||
(
|
||||
AlbertModel,
|
||||
AlbertForPreTraining,
|
||||
AlbertForMaskedLM,
|
||||
AlbertForMultipleChoice,
|
||||
AlbertForSequenceClassification,
|
||||
AlbertForTokenClassification,
|
||||
AlbertForQuestionAnswering,
|
||||
)
|
||||
if is_torch_available()
|
||||
else ()
|
||||
)
|
||||
fx_compatible = True
|
||||
|
||||
# special case for ForPreTraining model
|
||||
def _prepare_for_class(self, inputs_dict, model_class, return_labels=False):
|
||||
inputs_dict = super()._prepare_for_class(inputs_dict, model_class, return_labels=return_labels)
|
||||
|
||||
if return_labels:
|
||||
if model_class in get_values(MODEL_FOR_PRETRAINING_MAPPING):
|
||||
inputs_dict["labels"] = torch.zeros(
|
||||
(self.model_tester.batch_size, self.model_tester.seq_length), dtype=torch.long, device=torch_device
|
||||
)
|
||||
inputs_dict["sentence_order_label"] = torch.zeros(
|
||||
self.model_tester.batch_size, dtype=torch.long, device=torch_device
|
||||
)
|
||||
return inputs_dict
|
||||
|
||||
def setUp(self):
|
||||
self.model_tester = AlbertModelTester(self)
|
||||
self.config_tester = ConfigTester(self, config_class=AlbertConfig, hidden_size=37)
|
||||
|
||||
def test_config(self):
|
||||
self.config_tester.run_common_tests()
|
||||
|
||||
def test_model(self):
|
||||
config_and_inputs = self.model_tester.prepare_config_and_inputs()
|
||||
self.model_tester.create_and_check_model(*config_and_inputs)
|
||||
|
||||
def test_for_pretraining(self):
|
||||
config_and_inputs = self.model_tester.prepare_config_and_inputs()
|
||||
self.model_tester.create_and_check_for_pretraining(*config_and_inputs)
|
||||
|
||||
def test_for_masked_lm(self):
|
||||
config_and_inputs = self.model_tester.prepare_config_and_inputs()
|
||||
self.model_tester.create_and_check_for_masked_lm(*config_and_inputs)
|
||||
|
||||
def test_for_multiple_choice(self):
|
||||
config_and_inputs = self.model_tester.prepare_config_and_inputs()
|
||||
self.model_tester.create_and_check_for_multiple_choice(*config_and_inputs)
|
||||
|
||||
def test_for_question_answering(self):
|
||||
config_and_inputs = self.model_tester.prepare_config_and_inputs()
|
||||
self.model_tester.create_and_check_for_question_answering(*config_and_inputs)
|
||||
|
||||
def test_for_sequence_classification(self):
|
||||
config_and_inputs = self.model_tester.prepare_config_and_inputs()
|
||||
self.model_tester.create_and_check_for_sequence_classification(*config_and_inputs)
|
||||
|
||||
def test_model_various_embeddings(self):
|
||||
config_and_inputs = self.model_tester.prepare_config_and_inputs()
|
||||
for type in ["absolute", "relative_key", "relative_key_query"]:
|
||||
config_and_inputs[0].position_embedding_type = type
|
||||
self.model_tester.create_and_check_model(*config_and_inputs)
|
||||
|
||||
@slow
|
||||
def test_model_from_pretrained(self):
|
||||
for model_name in ALBERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]:
|
||||
model = AlbertModel.from_pretrained(model_name)
|
||||
self.assertIsNotNone(model)
|
||||
|
||||
|
||||
@require_torch
|
||||
class AlbertModelIntegrationTest(unittest.TestCase):
|
||||
@slow
|
||||
def test_inference_no_head_absolute_embedding(self):
|
||||
model = AlbertModel.from_pretrained("albert-base-v2")
|
||||
input_ids = torch.tensor([[0, 345, 232, 328, 740, 140, 1695, 69, 6078, 1588, 2]])
|
||||
attention_mask = torch.tensor([[0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]])
|
||||
with torch.no_grad():
|
||||
output = model(input_ids, attention_mask=attention_mask)[0]
|
||||
expected_shape = torch.Size((1, 11, 768))
|
||||
self.assertEqual(output.shape, expected_shape)
|
||||
expected_slice = torch.tensor(
|
||||
[[[-0.6513, 1.5035, -0.2766], [-0.6515, 1.5046, -0.2780], [-0.6512, 1.5049, -0.2784]]]
|
||||
)
|
||||
|
||||
self.assertTrue(torch.allclose(output[:, 1:4, 1:4], expected_slice, atol=1e-4))
|
||||
161
tests/models/albert/test_modeling_flax_albert.py
Normal file
161
tests/models/albert/test_modeling_flax_albert.py
Normal file
@@ -0,0 +1,161 @@
|
||||
# Copyright 2021 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.
|
||||
|
||||
import unittest
|
||||
|
||||
import numpy as np
|
||||
|
||||
from transformers import AlbertConfig, is_flax_available
|
||||
from transformers.testing_utils import require_flax, slow
|
||||
|
||||
from ...test_modeling_flax_common import FlaxModelTesterMixin, ids_tensor, random_attention_mask
|
||||
|
||||
|
||||
if is_flax_available():
|
||||
import jax.numpy as jnp
|
||||
from transformers.models.albert.modeling_flax_albert import (
|
||||
FlaxAlbertForMaskedLM,
|
||||
FlaxAlbertForMultipleChoice,
|
||||
FlaxAlbertForPreTraining,
|
||||
FlaxAlbertForQuestionAnswering,
|
||||
FlaxAlbertForSequenceClassification,
|
||||
FlaxAlbertForTokenClassification,
|
||||
FlaxAlbertModel,
|
||||
)
|
||||
|
||||
|
||||
class FlaxAlbertModelTester(unittest.TestCase):
|
||||
def __init__(
|
||||
self,
|
||||
parent,
|
||||
batch_size=13,
|
||||
seq_length=7,
|
||||
is_training=True,
|
||||
use_attention_mask=True,
|
||||
use_token_type_ids=True,
|
||||
use_labels=True,
|
||||
vocab_size=99,
|
||||
hidden_size=32,
|
||||
num_hidden_layers=5,
|
||||
num_attention_heads=4,
|
||||
intermediate_size=37,
|
||||
hidden_act="gelu",
|
||||
hidden_dropout_prob=0.1,
|
||||
attention_probs_dropout_prob=0.1,
|
||||
max_position_embeddings=512,
|
||||
type_vocab_size=16,
|
||||
type_sequence_label_size=2,
|
||||
initializer_range=0.02,
|
||||
num_choices=4,
|
||||
):
|
||||
self.parent = parent
|
||||
self.batch_size = batch_size
|
||||
self.seq_length = seq_length
|
||||
self.is_training = is_training
|
||||
self.use_attention_mask = use_attention_mask
|
||||
self.use_token_type_ids = use_token_type_ids
|
||||
self.use_labels = use_labels
|
||||
self.vocab_size = vocab_size
|
||||
self.hidden_size = hidden_size
|
||||
self.num_hidden_layers = num_hidden_layers
|
||||
self.num_attention_heads = num_attention_heads
|
||||
self.intermediate_size = intermediate_size
|
||||
self.hidden_act = hidden_act
|
||||
self.hidden_dropout_prob = hidden_dropout_prob
|
||||
self.attention_probs_dropout_prob = attention_probs_dropout_prob
|
||||
self.max_position_embeddings = max_position_embeddings
|
||||
self.type_vocab_size = type_vocab_size
|
||||
self.type_sequence_label_size = type_sequence_label_size
|
||||
self.initializer_range = initializer_range
|
||||
self.num_choices = num_choices
|
||||
|
||||
def prepare_config_and_inputs(self):
|
||||
input_ids = ids_tensor([self.batch_size, self.seq_length], self.vocab_size)
|
||||
|
||||
attention_mask = None
|
||||
if self.use_attention_mask:
|
||||
attention_mask = random_attention_mask([self.batch_size, self.seq_length])
|
||||
|
||||
token_type_ids = None
|
||||
if self.use_token_type_ids:
|
||||
token_type_ids = ids_tensor([self.batch_size, self.seq_length], self.type_vocab_size)
|
||||
|
||||
config = AlbertConfig(
|
||||
vocab_size=self.vocab_size,
|
||||
hidden_size=self.hidden_size,
|
||||
num_hidden_layers=self.num_hidden_layers,
|
||||
num_attention_heads=self.num_attention_heads,
|
||||
intermediate_size=self.intermediate_size,
|
||||
hidden_act=self.hidden_act,
|
||||
hidden_dropout_prob=self.hidden_dropout_prob,
|
||||
attention_probs_dropout_prob=self.attention_probs_dropout_prob,
|
||||
max_position_embeddings=self.max_position_embeddings,
|
||||
type_vocab_size=self.type_vocab_size,
|
||||
is_decoder=False,
|
||||
initializer_range=self.initializer_range,
|
||||
)
|
||||
|
||||
return config, input_ids, token_type_ids, attention_mask
|
||||
|
||||
def prepare_config_and_inputs_for_common(self):
|
||||
config_and_inputs = self.prepare_config_and_inputs()
|
||||
config, input_ids, token_type_ids, attention_mask = config_and_inputs
|
||||
inputs_dict = {"input_ids": input_ids, "token_type_ids": token_type_ids, "attention_mask": attention_mask}
|
||||
return config, inputs_dict
|
||||
|
||||
|
||||
@require_flax
|
||||
class FlaxAlbertModelTest(FlaxModelTesterMixin, unittest.TestCase):
|
||||
|
||||
all_model_classes = (
|
||||
(
|
||||
FlaxAlbertModel,
|
||||
FlaxAlbertForPreTraining,
|
||||
FlaxAlbertForMaskedLM,
|
||||
FlaxAlbertForMultipleChoice,
|
||||
FlaxAlbertForQuestionAnswering,
|
||||
FlaxAlbertForSequenceClassification,
|
||||
FlaxAlbertForTokenClassification,
|
||||
FlaxAlbertForQuestionAnswering,
|
||||
)
|
||||
if is_flax_available()
|
||||
else ()
|
||||
)
|
||||
|
||||
def setUp(self):
|
||||
self.model_tester = FlaxAlbertModelTester(self)
|
||||
|
||||
@slow
|
||||
def test_model_from_pretrained(self):
|
||||
for model_class_name in self.all_model_classes:
|
||||
model = model_class_name.from_pretrained("albert-base-v2")
|
||||
outputs = model(np.ones((1, 1)))
|
||||
self.assertIsNotNone(outputs)
|
||||
|
||||
|
||||
@require_flax
|
||||
class FlaxAlbertModelIntegrationTest(unittest.TestCase):
|
||||
@slow
|
||||
def test_inference_no_head_absolute_embedding(self):
|
||||
model = FlaxAlbertModel.from_pretrained("albert-base-v2")
|
||||
input_ids = np.array([[0, 345, 232, 328, 740, 140, 1695, 69, 6078, 1588, 2]])
|
||||
attention_mask = np.array([[0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]])
|
||||
output = model(input_ids, attention_mask=attention_mask)[0]
|
||||
expected_shape = (1, 11, 768)
|
||||
self.assertEqual(output.shape, expected_shape)
|
||||
expected_slice = np.array(
|
||||
[[[-0.6513, 1.5035, -0.2766], [-0.6515, 1.5046, -0.2780], [-0.6512, 1.5049, -0.2784]]]
|
||||
)
|
||||
|
||||
self.assertTrue(jnp.allclose(output[:, 1:4, 1:4], expected_slice, atol=1e-4))
|
||||
337
tests/models/albert/test_modeling_tf_albert.py
Normal file
337
tests/models/albert/test_modeling_tf_albert.py
Normal file
@@ -0,0 +1,337 @@
|
||||
# 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.
|
||||
|
||||
|
||||
import unittest
|
||||
|
||||
from transformers import AlbertConfig, is_tf_available
|
||||
from transformers.models.auto import get_values
|
||||
from transformers.testing_utils import require_tf, slow
|
||||
|
||||
from ...test_configuration_common import ConfigTester
|
||||
from ...test_modeling_tf_common import TFModelTesterMixin, ids_tensor, random_attention_mask
|
||||
|
||||
|
||||
if is_tf_available():
|
||||
import tensorflow as tf
|
||||
|
||||
from transformers import TF_MODEL_FOR_PRETRAINING_MAPPING
|
||||
from transformers.models.albert.modeling_tf_albert import (
|
||||
TF_ALBERT_PRETRAINED_MODEL_ARCHIVE_LIST,
|
||||
TFAlbertForMaskedLM,
|
||||
TFAlbertForMultipleChoice,
|
||||
TFAlbertForPreTraining,
|
||||
TFAlbertForQuestionAnswering,
|
||||
TFAlbertForSequenceClassification,
|
||||
TFAlbertForTokenClassification,
|
||||
TFAlbertModel,
|
||||
)
|
||||
|
||||
|
||||
class TFAlbertModelTester:
|
||||
def __init__(
|
||||
self,
|
||||
parent,
|
||||
batch_size=13,
|
||||
seq_length=7,
|
||||
is_training=True,
|
||||
use_input_mask=True,
|
||||
use_token_type_ids=True,
|
||||
use_labels=True,
|
||||
vocab_size=99,
|
||||
embedding_size=16,
|
||||
hidden_size=32,
|
||||
num_hidden_layers=5,
|
||||
num_attention_heads=4,
|
||||
intermediate_size=37,
|
||||
hidden_act="gelu",
|
||||
hidden_dropout_prob=0.1,
|
||||
attention_probs_dropout_prob=0.1,
|
||||
max_position_embeddings=512,
|
||||
type_vocab_size=16,
|
||||
type_sequence_label_size=2,
|
||||
initializer_range=0.02,
|
||||
num_labels=3,
|
||||
num_choices=4,
|
||||
scope=None,
|
||||
):
|
||||
self.parent = parent
|
||||
self.batch_size = 13
|
||||
self.seq_length = 7
|
||||
self.is_training = True
|
||||
self.use_input_mask = True
|
||||
self.use_token_type_ids = True
|
||||
self.use_labels = True
|
||||
self.vocab_size = 99
|
||||
self.embedding_size = 16
|
||||
self.hidden_size = 32
|
||||
self.num_hidden_layers = 5
|
||||
self.num_attention_heads = 4
|
||||
self.intermediate_size = 37
|
||||
self.hidden_act = "gelu"
|
||||
self.hidden_dropout_prob = 0.1
|
||||
self.attention_probs_dropout_prob = 0.1
|
||||
self.max_position_embeddings = 512
|
||||
self.type_vocab_size = 16
|
||||
self.type_sequence_label_size = 2
|
||||
self.initializer_range = 0.02
|
||||
self.num_labels = 3
|
||||
self.num_choices = 4
|
||||
self.scope = None
|
||||
|
||||
def prepare_config_and_inputs(self):
|
||||
input_ids = ids_tensor([self.batch_size, self.seq_length], self.vocab_size)
|
||||
|
||||
input_mask = None
|
||||
if self.use_input_mask:
|
||||
input_mask = random_attention_mask([self.batch_size, self.seq_length])
|
||||
|
||||
token_type_ids = None
|
||||
if self.use_token_type_ids:
|
||||
token_type_ids = ids_tensor([self.batch_size, self.seq_length], self.type_vocab_size)
|
||||
|
||||
sequence_labels = None
|
||||
token_labels = None
|
||||
choice_labels = None
|
||||
if self.use_labels:
|
||||
sequence_labels = ids_tensor([self.batch_size], self.type_sequence_label_size)
|
||||
token_labels = ids_tensor([self.batch_size, self.seq_length], self.num_labels)
|
||||
choice_labels = ids_tensor([self.batch_size], self.num_choices)
|
||||
|
||||
config = AlbertConfig(
|
||||
vocab_size=self.vocab_size,
|
||||
hidden_size=self.hidden_size,
|
||||
embedding_size=self.embedding_size,
|
||||
num_hidden_layers=self.num_hidden_layers,
|
||||
num_attention_heads=self.num_attention_heads,
|
||||
intermediate_size=self.intermediate_size,
|
||||
hidden_act=self.hidden_act,
|
||||
hidden_dropout_prob=self.hidden_dropout_prob,
|
||||
attention_probs_dropout_prob=self.attention_probs_dropout_prob,
|
||||
max_position_embeddings=self.max_position_embeddings,
|
||||
type_vocab_size=self.type_vocab_size,
|
||||
initializer_range=self.initializer_range,
|
||||
)
|
||||
|
||||
return config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
|
||||
def create_and_check_albert_model(
|
||||
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
):
|
||||
model = TFAlbertModel(config=config)
|
||||
# inputs = {'input_ids': input_ids,
|
||||
# 'attention_mask': input_mask,
|
||||
# 'token_type_ids': token_type_ids}
|
||||
# sequence_output, pooled_output = model(**inputs)
|
||||
inputs = {"input_ids": input_ids, "attention_mask": input_mask, "token_type_ids": token_type_ids}
|
||||
result = model(inputs)
|
||||
|
||||
inputs = [input_ids, input_mask]
|
||||
result = model(inputs)
|
||||
|
||||
result = model(input_ids)
|
||||
|
||||
self.parent.assertEqual(result.last_hidden_state.shape, (self.batch_size, self.seq_length, self.hidden_size))
|
||||
self.parent.assertEqual(result.pooler_output.shape, (self.batch_size, self.hidden_size))
|
||||
|
||||
def create_and_check_albert_for_pretraining(
|
||||
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
):
|
||||
config.num_labels = self.num_labels
|
||||
model = TFAlbertForPreTraining(config=config)
|
||||
inputs = {"input_ids": input_ids, "attention_mask": input_mask, "token_type_ids": token_type_ids}
|
||||
result = model(inputs)
|
||||
self.parent.assertEqual(result.prediction_logits.shape, (self.batch_size, self.seq_length, self.vocab_size))
|
||||
self.parent.assertEqual(result.sop_logits.shape, (self.batch_size, self.num_labels))
|
||||
|
||||
def create_and_check_albert_for_masked_lm(
|
||||
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
):
|
||||
model = TFAlbertForMaskedLM(config=config)
|
||||
inputs = {"input_ids": input_ids, "attention_mask": input_mask, "token_type_ids": token_type_ids}
|
||||
result = model(inputs)
|
||||
self.parent.assertEqual(result.logits.shape, (self.batch_size, self.seq_length, self.vocab_size))
|
||||
|
||||
def create_and_check_albert_for_sequence_classification(
|
||||
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
):
|
||||
config.num_labels = self.num_labels
|
||||
model = TFAlbertForSequenceClassification(config=config)
|
||||
inputs = {"input_ids": input_ids, "attention_mask": input_mask, "token_type_ids": token_type_ids}
|
||||
result = model(inputs)
|
||||
self.parent.assertEqual(result.logits.shape, (self.batch_size, self.num_labels))
|
||||
|
||||
def create_and_check_albert_for_question_answering(
|
||||
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
):
|
||||
model = TFAlbertForQuestionAnswering(config=config)
|
||||
inputs = {"input_ids": input_ids, "attention_mask": input_mask, "token_type_ids": token_type_ids}
|
||||
result = model(inputs)
|
||||
self.parent.assertEqual(result.start_logits.shape, (self.batch_size, self.seq_length))
|
||||
self.parent.assertEqual(result.end_logits.shape, (self.batch_size, self.seq_length))
|
||||
|
||||
def create_and_check_albert_for_multiple_choice(
|
||||
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
):
|
||||
config.num_choices = self.num_choices
|
||||
model = TFAlbertForMultipleChoice(config=config)
|
||||
multiple_choice_inputs_ids = tf.tile(tf.expand_dims(input_ids, 1), (1, self.num_choices, 1))
|
||||
multiple_choice_input_mask = tf.tile(tf.expand_dims(input_mask, 1), (1, self.num_choices, 1))
|
||||
multiple_choice_token_type_ids = tf.tile(tf.expand_dims(token_type_ids, 1), (1, self.num_choices, 1))
|
||||
inputs = {
|
||||
"input_ids": multiple_choice_inputs_ids,
|
||||
"attention_mask": multiple_choice_input_mask,
|
||||
"token_type_ids": multiple_choice_token_type_ids,
|
||||
}
|
||||
result = model(inputs)
|
||||
self.parent.assertListEqual(list(result["logits"].shape), [self.batch_size, self.num_choices])
|
||||
|
||||
def create_and_check_albert_for_token_classification(
|
||||
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
):
|
||||
config.num_labels = self.num_labels
|
||||
model = TFAlbertForTokenClassification(config=config)
|
||||
inputs = {
|
||||
"input_ids": input_ids,
|
||||
"attention_mask": input_mask,
|
||||
"token_type_ids": token_type_ids,
|
||||
}
|
||||
result = model(inputs)
|
||||
self.parent.assertListEqual(list(result["logits"].shape), [self.batch_size, self.seq_length, self.num_labels])
|
||||
|
||||
def prepare_config_and_inputs_for_common(self):
|
||||
config_and_inputs = self.prepare_config_and_inputs()
|
||||
(
|
||||
config,
|
||||
input_ids,
|
||||
token_type_ids,
|
||||
input_mask,
|
||||
sequence_labels,
|
||||
token_labels,
|
||||
choice_labels,
|
||||
) = config_and_inputs
|
||||
inputs_dict = {"input_ids": input_ids, "token_type_ids": token_type_ids, "attention_mask": input_mask}
|
||||
return config, inputs_dict
|
||||
|
||||
|
||||
@require_tf
|
||||
class TFAlbertModelTest(TFModelTesterMixin, unittest.TestCase):
|
||||
|
||||
all_model_classes = (
|
||||
(
|
||||
TFAlbertModel,
|
||||
TFAlbertForPreTraining,
|
||||
TFAlbertForMaskedLM,
|
||||
TFAlbertForSequenceClassification,
|
||||
TFAlbertForQuestionAnswering,
|
||||
TFAlbertForTokenClassification,
|
||||
TFAlbertForMultipleChoice,
|
||||
)
|
||||
if is_tf_available()
|
||||
else ()
|
||||
)
|
||||
test_head_masking = False
|
||||
test_onnx = False
|
||||
|
||||
# special case for ForPreTraining model
|
||||
def _prepare_for_class(self, inputs_dict, model_class, return_labels=False):
|
||||
inputs_dict = super()._prepare_for_class(inputs_dict, model_class, return_labels=return_labels)
|
||||
|
||||
if return_labels:
|
||||
if model_class in get_values(TF_MODEL_FOR_PRETRAINING_MAPPING):
|
||||
inputs_dict["sentence_order_label"] = tf.zeros(self.model_tester.batch_size, dtype=tf.int32)
|
||||
|
||||
return inputs_dict
|
||||
|
||||
def setUp(self):
|
||||
self.model_tester = TFAlbertModelTester(self)
|
||||
self.config_tester = ConfigTester(self, config_class=AlbertConfig, hidden_size=37)
|
||||
|
||||
def test_config(self):
|
||||
self.config_tester.run_common_tests()
|
||||
|
||||
def test_albert_model(self):
|
||||
config_and_inputs = self.model_tester.prepare_config_and_inputs()
|
||||
self.model_tester.create_and_check_albert_model(*config_and_inputs)
|
||||
|
||||
def test_for_pretraining(self):
|
||||
config_and_inputs = self.model_tester.prepare_config_and_inputs()
|
||||
self.model_tester.create_and_check_albert_for_pretraining(*config_and_inputs)
|
||||
|
||||
def test_for_masked_lm(self):
|
||||
config_and_inputs = self.model_tester.prepare_config_and_inputs()
|
||||
self.model_tester.create_and_check_albert_for_masked_lm(*config_and_inputs)
|
||||
|
||||
def test_for_multiple_choice(self):
|
||||
config_and_inputs = self.model_tester.prepare_config_and_inputs()
|
||||
self.model_tester.create_and_check_albert_for_multiple_choice(*config_and_inputs)
|
||||
|
||||
def test_for_sequence_classification(self):
|
||||
config_and_inputs = self.model_tester.prepare_config_and_inputs()
|
||||
self.model_tester.create_and_check_albert_for_sequence_classification(*config_and_inputs)
|
||||
|
||||
def test_for_question_answering(self):
|
||||
config_and_inputs = self.model_tester.prepare_config_and_inputs()
|
||||
self.model_tester.create_and_check_albert_for_question_answering(*config_and_inputs)
|
||||
|
||||
def test_model_common_attributes(self):
|
||||
config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common()
|
||||
list_lm_models = [TFAlbertForPreTraining, TFAlbertForMaskedLM]
|
||||
|
||||
for model_class in self.all_model_classes:
|
||||
model = model_class(config)
|
||||
assert isinstance(model.get_input_embeddings(), tf.keras.layers.Layer)
|
||||
|
||||
if model_class in list_lm_models:
|
||||
x = model.get_output_embeddings()
|
||||
assert isinstance(x, tf.keras.layers.Layer)
|
||||
name = model.get_bias()
|
||||
assert isinstance(name, dict)
|
||||
for k, v in name.items():
|
||||
assert isinstance(v, tf.Variable)
|
||||
else:
|
||||
x = model.get_output_embeddings()
|
||||
assert x is None
|
||||
name = model.get_bias()
|
||||
assert name is None
|
||||
|
||||
@slow
|
||||
def test_model_from_pretrained(self):
|
||||
for model_name in TF_ALBERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]:
|
||||
model = TFAlbertModel.from_pretrained(model_name)
|
||||
self.assertIsNotNone(model)
|
||||
|
||||
|
||||
@require_tf
|
||||
class TFAlbertModelIntegrationTest(unittest.TestCase):
|
||||
@slow
|
||||
def test_inference_masked_lm(self):
|
||||
model = TFAlbertForPreTraining.from_pretrained("albert-base-v2")
|
||||
input_ids = tf.constant([[0, 1, 2, 3, 4, 5]])
|
||||
output = model(input_ids)[0]
|
||||
|
||||
expected_shape = [1, 6, 30000]
|
||||
self.assertEqual(output.shape, expected_shape)
|
||||
|
||||
expected_slice = tf.constant(
|
||||
[
|
||||
[
|
||||
[4.595668, 0.74462754, -1.818147],
|
||||
[4.5954347, 0.7454184, -1.8188258],
|
||||
[4.5954905, 0.7448235, -1.8182316],
|
||||
]
|
||||
]
|
||||
)
|
||||
tf.debugging.assert_near(output[:, :3, :3], expected_slice, atol=1e-4)
|
||||
135
tests/models/albert/test_tokenization_albert.py
Normal file
135
tests/models/albert/test_tokenization_albert.py
Normal file
@@ -0,0 +1,135 @@
|
||||
# coding=utf-8
|
||||
# Copyright 2019 Hugging Face 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 AlbertTokenizer, AlbertTokenizerFast
|
||||
from transformers.testing_utils import get_tests_dir, require_sentencepiece, require_tokenizers, slow
|
||||
|
||||
from ...test_tokenization_common import TokenizerTesterMixin
|
||||
|
||||
|
||||
SAMPLE_VOCAB = get_tests_dir("fixtures/spiece.model")
|
||||
|
||||
|
||||
@require_sentencepiece
|
||||
@require_tokenizers
|
||||
class AlbertTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
|
||||
|
||||
tokenizer_class = AlbertTokenizer
|
||||
rust_tokenizer_class = AlbertTokenizerFast
|
||||
test_rust_tokenizer = True
|
||||
test_sentencepiece = True
|
||||
test_sentencepiece_ignore_case = True
|
||||
|
||||
def setUp(self):
|
||||
super().setUp()
|
||||
|
||||
# We have a SentencePiece fixture for testing
|
||||
tokenizer = AlbertTokenizer(SAMPLE_VOCAB)
|
||||
tokenizer.save_pretrained(self.tmpdirname)
|
||||
|
||||
def get_input_output_texts(self, tokenizer):
|
||||
input_text = "this is a test"
|
||||
output_text = "this is a test"
|
||||
return input_text, output_text
|
||||
|
||||
def test_convert_token_and_id(self):
|
||||
"""Test ``_convert_token_to_id`` and ``_convert_id_to_token``."""
|
||||
token = "<pad>"
|
||||
token_id = 0
|
||||
|
||||
self.assertEqual(self.get_tokenizer()._convert_token_to_id(token), token_id)
|
||||
self.assertEqual(self.get_tokenizer()._convert_id_to_token(token_id), token)
|
||||
|
||||
def test_get_vocab(self):
|
||||
vocab_keys = list(self.get_tokenizer().get_vocab().keys())
|
||||
|
||||
self.assertEqual(vocab_keys[0], "<pad>")
|
||||
self.assertEqual(vocab_keys[1], "<unk>")
|
||||
self.assertEqual(vocab_keys[-1], "▁eloquent")
|
||||
self.assertEqual(len(vocab_keys), 30_000)
|
||||
|
||||
def test_vocab_size(self):
|
||||
self.assertEqual(self.get_tokenizer().vocab_size, 30_000)
|
||||
|
||||
def test_rust_and_python_full_tokenizers(self):
|
||||
if not self.test_rust_tokenizer:
|
||||
return
|
||||
|
||||
tokenizer = self.get_tokenizer()
|
||||
rust_tokenizer = self.get_rust_tokenizer()
|
||||
|
||||
sequence = "I was born in 92000, and this is falsé."
|
||||
|
||||
tokens = tokenizer.tokenize(sequence)
|
||||
rust_tokens = rust_tokenizer.tokenize(sequence)
|
||||
self.assertListEqual(tokens, rust_tokens)
|
||||
|
||||
ids = tokenizer.encode(sequence, add_special_tokens=False)
|
||||
rust_ids = rust_tokenizer.encode(sequence, add_special_tokens=False)
|
||||
self.assertListEqual(ids, rust_ids)
|
||||
|
||||
rust_tokenizer = self.get_rust_tokenizer()
|
||||
ids = tokenizer.encode(sequence)
|
||||
rust_ids = rust_tokenizer.encode(sequence)
|
||||
self.assertListEqual(ids, rust_ids)
|
||||
|
||||
def test_full_tokenizer(self):
|
||||
tokenizer = AlbertTokenizer(SAMPLE_VOCAB, keep_accents=True)
|
||||
|
||||
tokens = tokenizer.tokenize("This is a test")
|
||||
self.assertListEqual(tokens, ["▁this", "▁is", "▁a", "▁test"])
|
||||
|
||||
self.assertListEqual(tokenizer.convert_tokens_to_ids(tokens), [48, 25, 21, 1289])
|
||||
|
||||
tokens = tokenizer.tokenize("I was born in 92000, and this is falsé.")
|
||||
self.assertListEqual(
|
||||
tokens, ["▁i", "▁was", "▁born", "▁in", "▁9", "2000", ",", "▁and", "▁this", "▁is", "▁fal", "s", "é", "."]
|
||||
)
|
||||
ids = tokenizer.convert_tokens_to_ids(tokens)
|
||||
self.assertListEqual(ids, [31, 23, 386, 19, 561, 3050, 15, 17, 48, 25, 8256, 18, 1, 9])
|
||||
|
||||
back_tokens = tokenizer.convert_ids_to_tokens(ids)
|
||||
self.assertListEqual(
|
||||
back_tokens,
|
||||
["▁i", "▁was", "▁born", "▁in", "▁9", "2000", ",", "▁and", "▁this", "▁is", "▁fal", "s", "<unk>", "."],
|
||||
)
|
||||
|
||||
def test_sequence_builders(self):
|
||||
tokenizer = AlbertTokenizer(SAMPLE_VOCAB)
|
||||
|
||||
text = tokenizer.encode("sequence builders")
|
||||
text_2 = tokenizer.encode("multi-sequence build")
|
||||
|
||||
encoded_sentence = tokenizer.build_inputs_with_special_tokens(text)
|
||||
encoded_pair = tokenizer.build_inputs_with_special_tokens(text, text_2)
|
||||
|
||||
assert encoded_sentence == [tokenizer.cls_token_id] + text + [tokenizer.sep_token_id]
|
||||
assert encoded_pair == [tokenizer.cls_token_id] + text + [tokenizer.sep_token_id] + text_2 + [
|
||||
tokenizer.sep_token_id
|
||||
]
|
||||
|
||||
@slow
|
||||
def test_tokenizer_integration(self):
|
||||
# fmt: off
|
||||
expected_encoding = {'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]], 'input_ids': [[2, 21970, 13, 5, 6092, 167, 28, 7103, 2153, 673, 8, 7028, 12051, 18, 17, 7103, 2153, 673, 8, 3515, 18684, 8, 4461, 6, 1927, 297, 8, 12060, 2607, 18, 13, 5, 4461, 15, 10538, 38, 8, 135, 15, 822, 58, 15, 993, 10363, 15, 1460, 8005, 4461, 15, 993, 255, 2328, 9, 9, 9, 6, 26, 1112, 816, 3260, 13, 5, 103, 2377, 6, 17, 1112, 816, 2782, 13, 5, 103, 10641, 6, 29, 84, 2512, 2430, 782, 18684, 2761, 19, 808, 2430, 2556, 17, 855, 1480, 9477, 4091, 128, 11712, 15, 7103, 2153, 673, 17, 24883, 9990, 9, 3], [2, 11502, 25, 1006, 20, 782, 8, 11809, 855, 1732, 19393, 18667, 37, 367, 21018, 69, 1854, 34, 11860, 19124, 27, 156, 225, 17, 193, 4141, 19, 65, 9124, 9, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [2, 14, 2231, 886, 2385, 17659, 84, 14, 16792, 1952, 9, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]], 'token_type_ids': [[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]]} # noqa: E501
|
||||
# fmt: on
|
||||
|
||||
self.tokenizer_integration_test_util(
|
||||
expected_encoding=expected_encoding,
|
||||
model_name="albert-base-v2",
|
||||
revision="6b6560eaf5ff2e250b00c50f380c5389a9c2d82e",
|
||||
)
|
||||
Reference in New Issue
Block a user