EngineX-Cambricon/enginex-mlu370-any2any
9
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

init

Browse Source
This commit is contained in:
luopingyi
2025-10-09 16:47:16 +08:00
parent c8feb4deb5
commit e27e3f16bb
5248 changed files with 1778505 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

0
transformers/tests/models/rembert/__init__.py Normal file
View File

482
transformers/tests/models/rembert/test_modeling_rembert.py Normal file
View File

@@ -0,0 +1,482 @@
# Copyright 2021 The HuggingFace Inc. 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.
"""Testing suite for the PyTorch RemBERT model."""
import unittest
from transformers import is_torch_available
from transformers.testing_utils import require_torch, slow, torch_device
from ...test_configuration_common import ConfigTester
from ...test_modeling_common import ModelTesterMixin, floats_tensor, ids_tensor, random_attention_mask
from ...test_pipeline_mixin import PipelineTesterMixin
if is_torch_available():
import torch
from transformers import (
RemBertConfig,
RemBertForCausalLM,
RemBertForMaskedLM,
RemBertForMultipleChoice,
RemBertForQuestionAnswering,
RemBertForSequenceClassification,
RemBertForTokenClassification,
RemBertModel,
)
class RemBertModelTester:
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,
hidden_size=32,
input_embedding_size=18,
output_embedding_size=43,
num_hidden_layers=2,
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 = batch_size
self.seq_length = seq_length
self.is_training = is_training
self.use_input_mask = use_input_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.input_embedding_size = input_embedding_size
self.output_embedding_size = output_embedding_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_labels = num_labels
self.num_choices = num_choices
self.scope = scope
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 = RemBertConfig(
vocab_size=self.vocab_size,
hidden_size=self.hidden_size,
input_embedding_size=self.input_embedding_size,
output_embedding_size=self.output_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,
is_decoder=False,
initializer_range=self.initializer_range,
)
return config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
def prepare_config_and_inputs_for_decoder(self):
(
config,
input_ids,
token_type_ids,
input_mask,
sequence_labels,
token_labels,
choice_labels,
) = self.prepare_config_and_inputs()
config.is_decoder = True
encoder_hidden_states = floats_tensor([self.batch_size, self.seq_length, self.hidden_size])
encoder_attention_mask = ids_tensor([self.batch_size, self.seq_length], vocab_size=2)
return (
config,
input_ids,
token_type_ids,
input_mask,
sequence_labels,
token_labels,
choice_labels,
encoder_hidden_states,
encoder_attention_mask,
)
def create_and_check_model(
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
):
model = RemBertModel(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))
def create_and_check_model_as_decoder(
self,
config,
input_ids,
token_type_ids,
input_mask,
sequence_labels,
token_labels,
choice_labels,
encoder_hidden_states,
encoder_attention_mask,
):
config.add_cross_attention = True
model = RemBertModel(config)
model.to(torch_device)
model.eval()
result = model(
input_ids,
attention_mask=input_mask,
token_type_ids=token_type_ids,
encoder_hidden_states=encoder_hidden_states,
encoder_attention_mask=encoder_attention_mask,
)
result = model(
input_ids,
attention_mask=input_mask,
token_type_ids=token_type_ids,
encoder_hidden_states=encoder_hidden_states,
)
result = model(input_ids, attention_mask=input_mask, token_type_ids=token_type_ids)
self.parent.assertEqual(result.last_hidden_state.shape, (self.batch_size, self.seq_length, self.hidden_size))
def create_and_check_for_masked_lm(
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
):
model = RemBertForMaskedLM(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_decoder_model_past_large_inputs(
self,
config,
input_ids,
token_type_ids,
input_mask,
sequence_labels,
token_labels,
choice_labels,
encoder_hidden_states,
encoder_attention_mask,
):
config.is_decoder = True
config.add_cross_attention = True
model = RemBertForCausalLM(config=config)
model.to(torch_device)
model.eval()
# first forward pass
outputs = model(
input_ids,
attention_mask=input_mask,
encoder_hidden_states=encoder_hidden_states,
encoder_attention_mask=encoder_attention_mask,
use_cache=True,
)
past_key_values = outputs.past_key_values
# create hypothetical multiple next token and extent to next_input_ids
next_tokens = ids_tensor((self.batch_size, 3), config.vocab_size)
next_mask = ids_tensor((self.batch_size, 3), vocab_size=2)
# append to next input_ids and
next_input_ids = torch.cat([input_ids, next_tokens], dim=-1)
next_attention_mask = torch.cat([input_mask, next_mask], dim=-1)
output_from_no_past = model(
next_input_ids,
attention_mask=next_attention_mask,
encoder_hidden_states=encoder_hidden_states,
encoder_attention_mask=encoder_attention_mask,
output_hidden_states=True,
)["hidden_states"][0]
output_from_past = model(
next_tokens,
attention_mask=next_attention_mask,
encoder_hidden_states=encoder_hidden_states,
encoder_attention_mask=encoder_attention_mask,
past_key_values=past_key_values,
output_hidden_states=True,
)["hidden_states"][0]
# select random slice
random_slice_idx = ids_tensor((1,), output_from_past.shape[-1]).item()
output_from_no_past_slice = output_from_no_past[:, -3:, random_slice_idx].detach()
output_from_past_slice = output_from_past[:, :, random_slice_idx].detach()
self.parent.assertTrue(output_from_past_slice.shape[1] == next_tokens.shape[1])
# test that outputs are equal for slice
self.parent.assertTrue(torch.allclose(output_from_past_slice, output_from_no_past_slice, atol=1e-3))
def create_and_check_for_question_answering(
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
):
model = RemBertForQuestionAnswering(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 = RemBertForSequenceClassification(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 = RemBertForTokenClassification(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 = RemBertForMultipleChoice(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 RemBertModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase):
all_model_classes = (
(
RemBertModel,
RemBertForMaskedLM,
RemBertForCausalLM,
RemBertForMultipleChoice,
RemBertForQuestionAnswering,
RemBertForSequenceClassification,
RemBertForTokenClassification,
)
if is_torch_available()
else ()
)
# Doesn't run generation tests. There are interface mismatches when using `generate` -- TODO @gante
all_generative_model_classes = ()
pipeline_model_mapping = (
{
"feature-extraction": RemBertModel,
"fill-mask": RemBertForMaskedLM,
"question-answering": RemBertForQuestionAnswering,
"text-classification": RemBertForSequenceClassification,
"text-generation": RemBertForCausalLM,
"token-classification": RemBertForTokenClassification,
"zero-shot": RemBertForSequenceClassification,
}
if is_torch_available()
else {}
)
def setUp(self):
self.model_tester = RemBertModelTester(self)
self.config_tester = ConfigTester(self, config_class=RemBertConfig, 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_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)
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_decoder_model_past_with_large_inputs(self):
config_and_inputs = self.model_tester.prepare_config_and_inputs_for_decoder()
self.model_tester.create_and_check_decoder_model_past_large_inputs(*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_for_token_classification(self):
config_and_inputs = self.model_tester.prepare_config_and_inputs()
self.model_tester.create_and_check_for_token_classification(*config_and_inputs)
def test_model_as_decoder(self):
config_and_inputs = self.model_tester.prepare_config_and_inputs_for_decoder()
self.model_tester.create_and_check_model_as_decoder(*config_and_inputs)
def test_model_as_decoder_with_default_input_mask(self):
(
config,
input_ids,
token_type_ids,
input_mask,
sequence_labels,
token_labels,
choice_labels,
encoder_hidden_states,
encoder_attention_mask,
) = self.model_tester.prepare_config_and_inputs_for_decoder()
input_mask = None
self.model_tester.create_and_check_model_as_decoder(
config,
input_ids,
token_type_ids,
input_mask,
sequence_labels,
token_labels,
choice_labels,
encoder_hidden_states,
encoder_attention_mask,
)
@slow
def test_model_from_pretrained(self):
model_name = "google/rembert"
model = RemBertModel.from_pretrained(model_name)
self.assertIsNotNone(model)
@require_torch
class RemBertModelIntegrationTest(unittest.TestCase):
@slow
def test_inference_model(self):
# Test exact values at the last hidden layer
model = RemBertModel.from_pretrained("google/rembert")
input_ids = torch.tensor([[312, 56498, 313, 2125, 313]])
segment_ids = torch.tensor([[0, 0, 0, 1, 1]])
with torch.no_grad():
output = model(input_ids, token_type_ids=segment_ids, output_hidden_states=True)
hidden_size = 1152
expected_shape = torch.Size((1, 5, hidden_size))
self.assertEqual(output["last_hidden_state"].shape, expected_shape)
expected_implementation = torch.tensor(
[
[
[0.0754, -0.2022, 0.1904],
[-0.3354, -0.3692, -0.4791],
[-0.2314, -0.6729, -0.0749],
[-0.0396, -0.3105, -0.4234],
[-0.1571, -0.0525, 0.5353],
]
]
)
torch.testing.assert_close(
output["last_hidden_state"][:, :, :3], expected_implementation, rtol=1e-4, atol=1e-4
)

248
transformers/tests/models/rembert/test_tokenization_rembert.py Normal file
View File

@@ -0,0 +1,248 @@
# Copyright 2022 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.
"""Testing suite for the RemBert tokenizer."""
import tempfile
import unittest
from tests.test_tokenization_common import AddedToken, TokenizerTesterMixin
from transformers import RemBertTokenizer, RemBertTokenizerFast
from transformers.testing_utils import get_tests_dir, require_sentencepiece, require_tokenizers
SENTENCEPIECE_UNDERLINE = "▁"
SPIECE_UNDERLINE = SENTENCEPIECE_UNDERLINE # Kept for backward compatibility
SAMPLE_VOCAB = get_tests_dir("fixtures/test_sentencepiece.model")
@require_sentencepiece
@require_tokenizers
class RemBertTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
from_pretrained_id = "google/rembert"
tokenizer_class = RemBertTokenizer
rust_tokenizer_class = RemBertTokenizerFast
space_between_special_tokens = True
test_rust_tokenizer = True
test_sentencepiece_ignore_case = True
pre_trained_model_path = "google/rembert"
@classmethod
def setUpClass(cls):
super().setUpClass()
tokenizer = RemBertTokenizer(SAMPLE_VOCAB)
tokenizer.save_pretrained(cls.tmpdirname)
# Copied from ReformerTokenizationTest.get_input_output_texts
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_get_vocab(self):
vocab_keys = list(self.get_tokenizer().get_vocab().keys())
self.assertEqual(vocab_keys[0], "<unk>")
self.assertEqual(vocab_keys[1], "<s>")
self.assertEqual(vocab_keys[5], "▁the")
self.assertEqual(vocab_keys[2], "</s>")
def test_vocab_size(self):
self.assertEqual(self.get_tokenizer().vocab_size, 1_000)
def test_full_tokenizer(self):
tokenizer = RemBertTokenizer(SAMPLE_VOCAB, keep_accents=True)
tokens = tokenizer.tokenize("This is a test")
self.assertListEqual(tokens, ["▁This", "▁is", "▁a", "▁t", "est"])
self.assertListEqual(
tokenizer.convert_tokens_to_ids(tokens),
[285, 46, 10, 170, 382],
)
tokens = tokenizer.tokenize("I was born in 92000, and this is falsé.")
self.assertListEqual( tokens, [SPIECE_UNDERLINE + "I",SPIECE_UNDERLINE + "was",SPIECE_UNDERLINE + "b","or","n",SPIECE_UNDERLINE + "in",SPIECE_UNDERLINE + "","9","2","0","0","0",",",SPIECE_UNDERLINE + "and",SPIECE_UNDERLINE + "this",SPIECE_UNDERLINE + "is",SPIECE_UNDERLINE + "f","al","s","é",".",],) # fmt: skip
ids = tokenizer.convert_tokens_to_ids(tokens)
self.assertListEqual(ids, [8, 21, 84, 55, 24, 19, 7, 0, 602, 347, 347, 347, 3, 12, 66, 46, 72, 80, 6, 0, 4])
def test_encode_decode_round_trip(self):
tokenizer = RemBertTokenizer(SAMPLE_VOCAB, keep_accents=True)
text = "清水寺は京都にある。"
tokens = tokenizer.tokenize(text)
self.assertListEqual(tokens, ["▁", "清水寺は京都にある。"])
encoded_string = tokenizer.encode(text)
self.assertListEqual(encoded_string, [1000, 7, 0, 1001])
decode_text = tokenizer.convert_tokens_to_string(tokens)
self.assertEqual(decode_text, text)
text = "That's awesome! 🤩 #HuggingFace, 🌟 Have a great day! 🌈"
tokens = tokenizer.tokenize(text)
self.assertListEqual( tokens, ['▁That', "'", 's', '▁a', 'w', 'es', 'ome', '!', '▁', '🤩', '▁', '#', 'H', 'u', 'g', 'g', 'ing', 'F', 'a', 'ce', ',', '▁', '🌟', '▁H', 'a', 've', '▁a', '▁great', '▁day', '!', '▁', '🌈']) # fmt: skip
decode_text = tokenizer.convert_tokens_to_string(tokens)
self.assertEqual(decode_text, "That's awesome! 🤩 #HuggingFace, 🌟 Have a great day! 🌈")
text = "In the sky up above"
tokens = tokenizer._tokenize(text)
self.assertListEqual(tokens, ["▁In", "▁the", "▁s", "k", "y", "▁up", "▁a", "b", "o", "ve"]) # fmt: skip
encoded_string = tokenizer.encode(text)
self.assertListEqual(encoded_string, [1000, 388, 5, 47, 45, 30, 118, 10, 65, 20, 123, 1001])
decode_text = tokenizer.convert_tokens_to_string(tokens)
self.assertEqual(text, decode_text)
text = "The cat. . Sat <s>.In a room"
tokens = tokenizer.tokenize(text)
self.assertListEqual(
tokens, ["▁The", "▁c", "at", ".", "▁", ".", "▁S", "at", "▁", "<", "s", ">", ".", "I", "n", "▁a", "▁room"]
)
encoded_string = tokenizer.encode(text)
self.assertListEqual(
encoded_string, [1000, 68, 69, 76, 4, 7, 4, 166, 76, 7, 0, 6, 0, 4, 100, 24, 10, 136, 1001]
)
decode_text = tokenizer.convert_tokens_to_string(tokens)
self.assertEqual(text, decode_text)
text = "Invoice #12345, dated 2023-12-01, is due on 2024-01-15."
tokens = tokenizer.tokenize(text)
self.assertListEqual(tokens, ['▁In', 'v', 'o', 'ic', 'e', '▁', '#', '1', '2', '34', '5', ',', '▁da', 'ted', '▁', '2', '0', '2', '3', '-', '1', '2', '-', '0', '1', ',', '▁is', '▁d', 'u', 'e', '▁on', '▁', '2', '0', '2', '4', '-', '0', '1', '-', '1', '5', '.']) # fmt: skip
encoded_string = tokenizer.encode(text)
self.assertListEqual(encoded_string, [1000, 388, 83, 20, 113, 15, 7, 0, 356, 602, 0, 555, 3, 417, 273, 7, 602, 347, 602, 0, 33, 356, 602, 33, 347, 356, 3, 46, 229, 51, 15, 59, 7, 602, 347, 602, 0, 33, 347, 356, 33, 356, 555, 4, 1001]) # fmt: skip
decode_text = tokenizer.convert_tokens_to_string(tokens)
self.assertEqual(text, decode_text)
text = "Lorem ipsum dolor sit amet, consectetur adipiscing elit..."
tokens = tokenizer.tokenize(text)
self.assertListEqual(tokens, ['▁', 'L', 'or', 'em', '▁', 'i', 'p', 's', 'um', '▁do', 'l', 'or', '▁sit', '▁am', 'e', 't', ',', '▁con', 'se', 'c', 'te', 't', 'ur', '▁a', 'd', 'i', 'p', 'is', 'c', 'ing', '▁', 'el', 'it', '.', '.', '.']) # fmt: skip
encoded_string = tokenizer.encode(text)
self.assertListEqual( encoded_string, [1000, 7, 279, 55, 300, 7, 23, 29, 6, 155, 92, 27, 55, 615, 219, 15, 14, 3, 247, 114, 28, 181, 14, 108, 10, 16, 23, 29, 125, 28, 17, 7, 168, 137, 4, 4, 4, 1001] ) # fmt: skip
decode_text = tokenizer.convert_tokens_to_string(tokens)
self.assertEqual(text, decode_text)
# for multiple language in one sentence
text = "Bonjour! Hello! こんにちは!"
tokens = tokenizer.tokenize(text)
self.assertListEqual(tokens, ["▁B", "on", "j", "o", "ur", "!", "▁He", "ll", "o", "!", "▁", "こんにちは", "!"])
encoded_string = tokenizer.encode(text)
self.assertListEqual(encoded_string, [1000, 295, 109, 999, 20, 108, 146, 156, 86, 20, 146, 7, 0, 146, 1001])
decode_text = tokenizer.convert_tokens_to_string(tokens)
self.assertEqual(text, decode_text)
text = "Extra spaces\tand\nline breaks\r\nshould be handled."
tokens = tokenizer.tokenize(text)
self.assertListEqual(tokens, ['▁E', 'x', 't', 'r', 'a', '▁sp', 'a', 'ce', 's', '▁and', '▁line', '▁b', 're', 'a', 'k', 's', '▁should', '▁be', '▁hand', 'led', '.']) # fmt: skip
encoded_string = tokenizer.encode(text)
self.assertListEqual(
encoded_string,
[1000, 454, 297, 14, 35, 18, 277, 18, 133, 6, 12, 485, 84, 56, 18, 45, 6, 173, 36, 363, 338, 4, 1001],
)
decode_text = tokenizer.convert_tokens_to_string(tokens)
self.assertEqual("Extra spaces and line breaks should be handled.", decode_text)
def test_sequence_builders(self):
tokenizer = RemBertTokenizer(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
]
def test_added_tokens_serialization(self):
# Utility to test the added vocab
def _test_added_vocab_and_eos(expected, tokenizer_class, expected_eos, temp_dir):
tokenizer = tokenizer_class.from_pretrained(temp_dir)
self.assertTrue(str(expected_eos) not in tokenizer.additional_special_tokens)
self.assertIn(new_eos, tokenizer.added_tokens_decoder.values())
self.assertEqual(tokenizer.added_tokens_decoder[tokenizer.eos_token_id], new_eos)
self.assertTrue(all(item in tokenizer.added_tokens_decoder.items() for item in expected.items()))
return tokenizer
new_eos = AddedToken("[NEW_EOS]", rstrip=False, lstrip=True, normalized=False, special=True)
new_masked_token = AddedToken("[MASK]", lstrip=True, rstrip=False, normalized=False)
for tokenizer, pretrained_name, kwargs in self.tokenizers_list:
with self.subTest(f"{tokenizer.__class__.__name__} ({pretrained_name})"):
# Load a slow tokenizer from the hub, init with the new token for fast to also include it
tokenizer = self.tokenizer_class.from_pretrained(
pretrained_name, eos_token=new_eos, mask_token=new_masked_token
)
EXPECTED_ADDED_TOKENS_DECODER = tokenizer.added_tokens_decoder
with self.subTest("Hub -> Slow: Test loading a slow tokenizer from the hub)"):
self.assertEqual(tokenizer._special_tokens_map["eos_token"], new_eos)
self.assertIn(new_eos, list(tokenizer.added_tokens_decoder.values()))
with tempfile.TemporaryDirectory() as tmp_dir_2:
tokenizer.save_pretrained(tmp_dir_2)
with self.subTest(
"Hub -> Slow -> Slow: Test saving this slow tokenizer and reloading it in the fast class"
):
_test_added_vocab_and_eos(
EXPECTED_ADDED_TOKENS_DECODER, self.tokenizer_class, new_eos, tmp_dir_2
)
if self.rust_tokenizer_class is not None:
with self.subTest(
"Hub -> Slow -> Fast: Test saving this slow tokenizer and reloading it in the fast class"
):
tokenizer_fast = _test_added_vocab_and_eos(
EXPECTED_ADDED_TOKENS_DECODER, self.rust_tokenizer_class, new_eos, tmp_dir_2
)
with tempfile.TemporaryDirectory() as tmp_dir_3:
tokenizer_fast.save_pretrained(tmp_dir_3)
with self.subTest(
"Hub -> Slow -> Fast -> Fast: Test saving this fast tokenizer and reloading it in the fast class"
):
_test_added_vocab_and_eos(
EXPECTED_ADDED_TOKENS_DECODER, self.rust_tokenizer_class, new_eos, tmp_dir_3
)
with self.subTest(
"Hub -> Slow -> Fast -> Slow: Test saving this slow tokenizer and reloading it in the slow class"
):
_test_added_vocab_and_eos(
EXPECTED_ADDED_TOKENS_DECODER, self.rust_tokenizer_class, new_eos, tmp_dir_3
)
with self.subTest("Hub -> Fast: Test loading a fast tokenizer from the hub)"):
if self.rust_tokenizer_class is not None:
tokenizer_fast = self.get_rust_tokenizer(pretrained_name, eos_token=new_eos)
self.assertEqual(tokenizer_fast._special_tokens_map["eos_token"], new_eos)
self.assertIn(new_eos, list(tokenizer_fast.added_tokens_decoder.values()))
# We can't test the following because for BC we kept the default rstrip lstrip in slow not fast. Will comment once normalization is alright
with self.subTest("Hub -> Fast == Hub -> Slow: make sure slow and fast tokenizer match"):
self.assertTrue(
all(
item in tokenizer.added_tokens_decoder.items()
for item in EXPECTED_ADDED_TOKENS_DECODER.items()
)
)
EXPECTED_ADDED_TOKENS_DECODER = tokenizer_fast.added_tokens_decoder
with tempfile.TemporaryDirectory() as tmp_dir_4:
tokenizer_fast.save_pretrained(tmp_dir_4)
with self.subTest("Hub -> Fast -> Fast: saving Fast1 locally and loading"):
_test_added_vocab_and_eos(
EXPECTED_ADDED_TOKENS_DECODER, self.rust_tokenizer_class, new_eos, tmp_dir_4
)
with self.subTest("Hub -> Fast -> Slow: saving Fast1 locally and loading"):
_test_added_vocab_and_eos(
EXPECTED_ADDED_TOKENS_DECODER, self.tokenizer_class, new_eos, tmp_dir_4
)