Skip to content

roc_bert

mindnlp.transformers.models.roc_bert.configuration_roc_bert

RoCBert model configuration

mindnlp.transformers.models.roc_bert.configuration_roc_bert.RoCBertConfig

Bases: PretrainedConfig

This is the configuration class to store the configuration of a [RoCBertModel]. It is used to instantiate a RoCBert model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the RoCBert weiweishi/roc-bert-base-zh architecture.

Configuration objects inherit from [PretrainedConfig] and can be used to control the model outputs. Read the documentation from [PretrainedConfig] for more information.

PARAMETER DESCRIPTION
vocab_size

Vocabulary size of the RoCBert model. Defines the number of different tokens that can be represented by the inputs_ids passed when calling [RoCBertModel].

TYPE: `int`, *optional*, defaults to 30522 DEFAULT: 30522

hidden_size

Dimension of the encoder layers and the pooler layer.

TYPE: `int`, *optional*, defaults to 768 DEFAULT: 768

num_hidden_layers

Number of hidden layers in the Transformer encoder.

TYPE: `int`, *optional*, defaults to 12 DEFAULT: 12

num_attention_heads

Number of attention heads for each attention layer in the Transformer encoder.

TYPE: `int`, *optional*, defaults to 12 DEFAULT: 12

intermediate_size

Dimension of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.

TYPE: `int`, *optional*, defaults to 3072 DEFAULT: 3072

hidden_act

The non-linear activation function (function or string) in the encoder and pooler. If string, "gelu", "relu", "selu" and "gelu_new" are supported.

TYPE: `str` or `function`, *optional*, defaults to `"gelu"` DEFAULT: 'gelu'

hidden_dropout_prob

The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.

TYPE: `float`, *optional*, defaults to 0.1 DEFAULT: 0.1

attention_probs_dropout_prob

The dropout ratio for the attention probabilities.

TYPE: `float`, *optional*, defaults to 0.1 DEFAULT: 0.1

max_position_embeddings

The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048).

TYPE: `int`, *optional*, defaults to 512 DEFAULT: 512

type_vocab_size

The vocabulary size of the token_type_ids passed when calling [RoCBertModel].

TYPE: `int`, *optional*, defaults to 2 DEFAULT: 2

initializer_range

The standard deviation of the truncated_normal_initializer for initializing all weight matrices.

TYPE: `float`, *optional*, defaults to 0.02 DEFAULT: 0.02

layer_norm_eps

The epsilon used by the layer normalization layers.

TYPE: `float`, *optional*, defaults to 1e-12 DEFAULT: 1e-12

is_decoder

Whether the model is used as a decoder or not. If False, the model is used as an encoder.

TYPE: `bool`, *optional*, defaults to `False`

use_cache

Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if config.is_decoder=True.

TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True

position_embedding_type

Type of position embedding. Choose one of "absolute", "relative_key", "relative_key_query". For positional embeddings use "absolute". For more information on "relative_key", please refer to Self-Attention with Relative Position Representations (Shaw et al.). For more information on "relative_key_query", please refer to Method 4 in Improve Transformer Models with Better Relative Position Embeddings (Huang et al.).

TYPE: `str`, *optional*, defaults to `"absolute"` DEFAULT: 'absolute'

classifier_dropout

The dropout ratio for the classification head.

TYPE: `float`, *optional* DEFAULT: None

enable_pronunciation

Whether or not the model use pronunciation embed when training.

TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True

enable_shape

Whether or not the model use shape embed when training.

TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True

pronunciation_embed_dim

Dimension of the pronunciation_embed.

TYPE: `int`, *optional*, defaults to 768 DEFAULT: 768

pronunciation_vocab_size

Pronunciation Vocabulary size of the RoCBert model. Defines the number of different tokens that can be represented by the input_pronunciation_ids passed when calling [RoCBertModel].

TYPE: `int`, *optional*, defaults to 910 DEFAULT: 910

shape_embed_dim

Dimension of the shape_embed.

TYPE: `int`, *optional*, defaults to 512 DEFAULT: 512

shape_vocab_size

Shape Vocabulary size of the RoCBert model. Defines the number of different tokens that can be represented by the input_shape_ids passed when calling [RoCBertModel].

TYPE: `int`, *optional*, defaults to 24858 DEFAULT: 24858

concat_input

Defines the way of merging the shape_embed, pronunciation_embed and word_embed, if the value is true, output_embed = torch.cat((word_embed, shape_embed, pronunciation_embed), -1), else output_embed = (word_embed + shape_embed + pronunciation_embed) / 3

TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True

Example 
>>> from transformers import RoCBertModel, RoCBertConfig
...
>>> # Initializing a RoCBert weiweishi/roc-bert-base-zh style configuration
>>> configuration = RoCBertConfig()
...
>>> # Initializing a model from the weiweishi/roc-bert-base-zh style configuration
>>> model = RoCBertModel(configuration)
...
>>> # Accessing the model configuration
>>> configuration = model.config
Source code in mindnlp/transformers/models/roc_bert/configuration_roc_bert.py 
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
class RoCBertConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`RoCBertModel`]. It is used to instantiate a
    RoCBert model according to the specified arguments, defining the model architecture. Instantiating a configuration
    with the defaults will yield a similar configuration to that of the RoCBert
    [weiweishi/roc-bert-base-zh](https://huggingface.co/weiweishi/roc-bert-base-zh) architecture.

    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
    documentation from [`PretrainedConfig`] for more information.


    Args:
        vocab_size (`int`, *optional*, defaults to 30522):
            Vocabulary size of the RoCBert model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`RoCBertModel`].
        hidden_size (`int`, *optional*, defaults to 768):
            Dimension of the encoder layers and the pooler layer.
        num_hidden_layers (`int`, *optional*, defaults to 12):
            Number of hidden layers in the Transformer encoder.
        num_attention_heads (`int`, *optional*, defaults to 12):
            Number of attention heads for each attention layer in the Transformer encoder.
        intermediate_size (`int`, *optional*, defaults to 3072):
            Dimension of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
        hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`):
            The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
            `"relu"`, `"selu"` and `"gelu_new"` are supported.
        hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
        attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
            The dropout ratio for the attention probabilities.
        max_position_embeddings (`int`, *optional*, defaults to 512):
            The maximum sequence length that this model might ever be used with. Typically set this to something large
            just in case (e.g., 512 or 1024 or 2048).
        type_vocab_size (`int`, *optional*, defaults to 2):
            The vocabulary size of the `token_type_ids` passed when calling [`RoCBertModel`].
        initializer_range (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        layer_norm_eps (`float`, *optional*, defaults to 1e-12):
            The epsilon used by the layer normalization layers.
        is_decoder (`bool`, *optional*, defaults to `False`):
            Whether the model is used as a decoder or not. If `False`, the model is used as an encoder.
        use_cache (`bool`, *optional*, defaults to `True`):
            Whether or not the model should return the last key/values attentions (not used by all models). Only
            relevant if `config.is_decoder=True`.
        position_embedding_type (`str`, *optional*, defaults to `"absolute"`):
            Type of position embedding. Choose one of `"absolute"`, `"relative_key"`, `"relative_key_query"`. For
            positional embeddings use `"absolute"`. For more information on `"relative_key"`, please refer to
            [Self-Attention with Relative Position Representations (Shaw et al.)](https://arxiv.org/abs/1803.02155).
            For more information on `"relative_key_query"`, please refer to *Method 4* in [Improve Transformer Models
            with Better Relative Position Embeddings (Huang et al.)](https://arxiv.org/abs/2009.13658).
        classifier_dropout (`float`, *optional*):
            The dropout ratio for the classification head.
        enable_pronunciation (`bool`, *optional*, defaults to `True`):
            Whether or not the model use pronunciation embed when training.
        enable_shape (`bool`, *optional*, defaults to `True`):
            Whether or not the model use shape embed when training.
        pronunciation_embed_dim (`int`, *optional*, defaults to 768):
            Dimension of the pronunciation_embed.
        pronunciation_vocab_size (`int`, *optional*, defaults to 910):
            Pronunciation Vocabulary size of the RoCBert model. Defines the number of different tokens that can be
            represented by the `input_pronunciation_ids` passed when calling [`RoCBertModel`].
        shape_embed_dim (`int`, *optional*, defaults to 512):
            Dimension of the shape_embed.
        shape_vocab_size (`int`, *optional*, defaults to 24858):
            Shape Vocabulary size of the RoCBert model. Defines the number of different tokens that can be represented
            by the `input_shape_ids` passed when calling [`RoCBertModel`].
        concat_input (`bool`, *optional*, defaults to `True`):
            Defines the way of merging the shape_embed, pronunciation_embed and word_embed, if the value is true,
            output_embed = torch.cat((word_embed, shape_embed, pronunciation_embed), -1), else output_embed =
            (word_embed + shape_embed + pronunciation_embed) / 3

    Example:
        ```python
        >>> from transformers import RoCBertModel, RoCBertConfig
        ...
        >>> # Initializing a RoCBert weiweishi/roc-bert-base-zh style configuration
        >>> configuration = RoCBertConfig()
        ...
        >>> # Initializing a model from the weiweishi/roc-bert-base-zh style configuration
        >>> model = RoCBertModel(configuration)
        ...
        >>> # Accessing the model configuration
        >>> configuration = model.config
        ```
    """

    model_type = "roc_bert"

    def __init__(
        self,
        vocab_size=30522,
        hidden_size=768,
        num_hidden_layers=12,
        num_attention_heads=12,
        intermediate_size=3072,
        hidden_act="gelu",
        hidden_dropout_prob=0.1,
        attention_probs_dropout_prob=0.1,
        max_position_embeddings=512,
        type_vocab_size=2,
        initializer_range=0.02,
        layer_norm_eps=1e-12,
        use_cache=True,
        pad_token_id=0,
        position_embedding_type="absolute",
        classifier_dropout=None,
        enable_pronunciation=True,
        enable_shape=True,
        pronunciation_embed_dim=768,
        pronunciation_vocab_size=910,
        shape_embed_dim=512,
        shape_vocab_size=24858,
        concat_input=True,
        **kwargs,
    ):
        self.vocab_size = vocab_size
        self.max_position_embeddings = max_position_embeddings
        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.initializer_range = initializer_range
        self.type_vocab_size = type_vocab_size
        self.layer_norm_eps = layer_norm_eps
        self.use_cache = use_cache
        self.enable_pronunciation = enable_pronunciation
        self.enable_shape = enable_shape
        self.pronunciation_embed_dim = pronunciation_embed_dim
        self.pronunciation_vocab_size = pronunciation_vocab_size
        self.shape_embed_dim = shape_embed_dim
        self.shape_vocab_size = shape_vocab_size
        self.concat_input = concat_input
        self.position_embedding_type = position_embedding_type
        self.classifier_dropout = classifier_dropout
        super().__init__(pad_token_id=pad_token_id, **kwargs)

mindnlp.transformers.models.roc_bert.modeling_roc_bert

MindSpore RoCBert model.

mindnlp.transformers.models.roc_bert.modeling_roc_bert.RoCBertEmbeddings

Bases: Module

Construct the embeddings from word, position, shape, pronunciation and token_type embeddings.

Source code in mindnlp/transformers/models/roc_bert/modeling_roc_bert.py 
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
class RoCBertEmbeddings(nn.Module):
    """Construct the embeddings from word, position, shape, pronunciation and token_type embeddings."""

    def __init__(self, config):
        super().__init__()
        self.word_embeddings = nn.Embedding(
            config.vocab_size, config.hidden_size, padding_idx=config.pad_token_id
        )
        self.pronunciation_embed = nn.Embedding(
            config.pronunciation_vocab_size,
            config.pronunciation_embed_dim,
            padding_idx=config.pad_token_id,
        )
        self.shape_embed = nn.Embedding(
            config.shape_vocab_size,
            config.shape_embed_dim,
            padding_idx=config.pad_token_id,
        )
        self.position_embeddings = nn.Embedding(
            config.max_position_embeddings, config.hidden_size
        )
        self.token_type_embeddings = nn.Embedding(
            config.type_vocab_size, config.hidden_size
        )

        self.enable_pronunciation = config.enable_pronunciation
        self.enable_shape = config.enable_shape

        if config.concat_input:
            input_dim = config.hidden_size
            if self.enable_pronunciation:
                pronunciation_dim = config.pronunciation_embed_dim
                input_dim += pronunciation_dim
            if self.enable_shape:
                shape_dim = config.shape_embed_dim
                input_dim += shape_dim
            self.map_inputs_layer = nn.Linear(input_dim, config.hidden_size)
        else:
            self.map_inputs_layer = None

        # self.LayerNorm is not snake-cased to stick with TensorFlow model variable name and be able to load
        # any TensorFlow checkpoint file
        self.LayerNorm = nn.LayerNorm(
            [config.hidden_size], eps=config.layer_norm_eps
        )
        self.dropout = nn.Dropout(p=config.hidden_dropout_prob)

        # position_ids (1, len position emb) is contiguous in memory and exported when serialized
        self.position_ids = ops.arange(config.max_position_embeddings).broadcast_to(
            (1, -1)
        )
        self.position_embedding_type = getattr(
            config, "position_embedding_type", "absolute"
        )
        self.token_type_ids = ops.zeros(self.position_ids.shape, dtype=mindspore.int64)

    def forward(
        self,
        input_ids=None,
        input_shape_ids=None,
        input_pronunciation_ids=None,
        token_type_ids=None,
        position_ids=None,
        inputs_embeds=None,
        past_key_values_length=0,
    ):
        if input_ids is not None:
            input_shape = input_ids.shape
        else:
            input_shape = inputs_embeds.shape[:-1]

        seq_length = input_shape[1]

        if position_ids is None:
            position_ids = self.position_ids[
                :, past_key_values_length : seq_length + past_key_values_length
            ]

        # Setting the token_type_ids to the registered buffer in forwardor where it is all zeros, which usually occurs
        # when its auto-generated, registered buffer helps users when tracing the model without passing token_type_ids, solves
        # issue #5664
        if token_type_ids is None:
            if hasattr(self, "token_type_ids"):
                buffered_token_type_ids = self.token_type_ids[:, :seq_length]
                buffered_token_type_ids_expanded = buffered_token_type_ids.broadcast_to(
                    (input_shape[0], seq_length)
                )
                token_type_ids = buffered_token_type_ids_expanded
            else:
                token_type_ids = ops.zeros(input_shape, dtype=mindspore.int64)

        if self.map_inputs_layer is None:
            if inputs_embeds is None:
                inputs_embeds = self.word_embeddings(input_ids)
            token_type_embeddings = self.token_type_embeddings(token_type_ids)
            embeddings = inputs_embeds + token_type_embeddings
            if self.position_embedding_type == "absolute":
                position_embeddings = self.position_embeddings(position_ids)
                embeddings += position_embeddings
            embeddings = self.LayerNorm(embeddings)
            embeddings = self.dropout(embeddings)

            denominator = 1
            embedding_in = embeddings
            if self.enable_shape and input_shape_ids is not None:
                embedding_shape = self.shape_embed(input_shape_ids)
                embedding_in += embedding_shape
                denominator += 1
            if self.enable_pronunciation and input_pronunciation_ids is not None:
                embedding_pronunciation = self.pronunciation_embed(
                    input_pronunciation_ids
                )
                embedding_in += embedding_pronunciation
                denominator += 1

            embedding_in /= denominator
            return embedding_in
        else:
            if inputs_embeds is None:
                inputs_embeds = self.word_embeddings(input_ids)  # embedding_word

            embedding_in = inputs_embeds
            if self.enable_shape:
                if input_shape_ids is None:
                    input_shape_ids = ops.zeros(input_shape, dtype=mindspore.int64)
                embedding_shape = self.shape_embed(input_shape_ids)
                embedding_in = ops.cat((embedding_in, embedding_shape), -1)
            if self.enable_pronunciation:
                if input_pronunciation_ids is None:
                    input_pronunciation_ids = ops.zeros(
                        input_shape, dtype=mindspore.int64
                    )
                embedding_pronunciation = self.pronunciation_embed(
                    input_pronunciation_ids
                )
                embedding_in = ops.cat((embedding_in, embedding_pronunciation), -1)

            embedding_in = self.map_inputs_layer(
                embedding_in
            )  # batch_size * seq_len * hidden_dim

            token_type_embeddings = self.token_type_embeddings(token_type_ids)
            embedding_in += token_type_embeddings
            if self.position_embedding_type == "absolute":
                position_embeddings = self.position_embeddings(position_ids)
                embedding_in += position_embeddings

            embedding_in = self.LayerNorm(embedding_in)
            embedding_in = self.dropout(embedding_in)
            return embedding_in

mindnlp.transformers.models.roc_bert.modeling_roc_bert.RoCBertForCausalLM

Bases: RoCBertPreTrainedModel

Source code in mindnlp/transformers/models/roc_bert/modeling_roc_bert.py 
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
class RoCBertForCausalLM(RoCBertPreTrainedModel):
    _tied_weights_keys = [
        "cls.predictions.decoder.weight",
        "cls.predictions.decoder.bias",
    ]

    # Copied from transformers.models.bert.modeling_bert.BertLMHeadModel.__init__ with BertLMHeadModel->RoCBertForCausalLM,Bert->RoCBert,bert->roc_bert
    def __init__(self, config):
        super().__init__(config)

        if not config.is_decoder:
            logger.warning(
                "If you want to use `RoCRoCBertForCausalLM` as a standalone, add `is_decoder=True.`"
            )

        self.roc_bert = RoCBertModel(config, add_pooling_layer=False)
        self.cls = RoCBertOnlyMLMHead(config)

        # Initialize weights and apply final processing
        self.post_init()

    # Copied from transformers.models.bert.modeling_bert.BertLMHeadModel.get_output_embeddings
    def get_output_embeddings(self):
        return self.cls.predictions.decoder

    # Copied from transformers.models.bert.modeling_bert.BertLMHeadModel.set_output_embeddings
    def set_output_embeddings(self, new_embeddings):
        self.cls.predictions.decoder = new_embeddings
        self.cls.predictions.bias = new_embeddings.bias

    def forward(
        self,
        input_ids: Optional[mindspore.Tensor] = None,
        input_shape_ids: Optional[mindspore.Tensor] = None,
        input_pronunciation_ids: Optional[mindspore.Tensor] = None,
        attention_mask: Optional[mindspore.Tensor] = None,
        token_type_ids: Optional[mindspore.Tensor] = None,
        position_ids: Optional[mindspore.Tensor] = None,
        inputs_embeds: Optional[mindspore.Tensor] = None,
        encoder_hidden_states: Optional[mindspore.Tensor] = None,
        encoder_attention_mask: Optional[mindspore.Tensor] = None,
        head_mask: Optional[mindspore.Tensor] = None,
        past_key_values: Optional[List[mindspore.Tensor]] = None,
        labels: Optional[mindspore.Tensor] = None,
        use_cache: Optional[bool] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
    ) -> Union[Tuple[mindspore.Tensor], CausalLMOutputWithCrossAttentions]:
        r"""
        Args:
            encoder_hidden_states  (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
                Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if
                the model is configured as a decoder.
            encoder_attention_mask (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*):
                Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in
                the cross-attention if the model is configured as a decoder. Mask values selected in `[0, 1]`:

                - 1 for tokens that are **not masked**,
                - 0 for tokens that are **masked**.
            past_key_values (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
                Tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of shape
                `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and 2 additional tensors of shape
                `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`. The two additional tensors are
                only required when the model is used as a decoder in a Sequence to Sequence model.

                Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention
                blocks) that can be used (see `past_key_values` input) to speed up sequential decoding.

                If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those that
                don't have their past key value states given to this model) of shape `(batch_size, 1)` instead of all
                `decoder_input_ids` of shape `(batch_size, sequence_length)`.
            labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
                Labels for computing the left-to-right language modeling loss (next word prediction). Indices should be in
                `[-100, 0, ..., config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are
                ignored (masked), the loss is only computed for the tokens with labels n `[0, ..., config.vocab_size]`.
            use_cache (`bool`, *optional*):
                If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see
                `past_key_values`).

        Returns:
            `Union[Tuple[mindspore.Tensor], CausalLMOutputWithCrossAttentions]`

        Example:
            ```python
            >>> from transformers import AutoTokenizer, RoCBertForCausalLM, RoCBertConfig
            >>> import torch
            ...
            >>> tokenizer = AutoTokenizer.from_pretrained("weiweishi/roc-bert-base-zh")
            >>> config = RoCBertConfig.from_pretrained("weiweishi/roc-bert-base-zh")
            >>> config.is_decoder = True
            >>> model = RoCBertForCausalLM.from_pretrained("weiweishi/roc-bert-base-zh", config=config)
            ...
            >>> inputs = tokenizer("你好，很高兴认识你", return_tensors="pt")
            >>> outputs = model(**inputs)
            ...
            >>> prediction_logits = outputs.logits
            ```
        """
        return_dict = (
            return_dict if return_dict is not None else self.config.use_return_dict
        )

        outputs = self.roc_bert(
            input_ids,
            input_shape_ids=input_shape_ids,
            input_pronunciation_ids=input_pronunciation_ids,
            attention_mask=attention_mask,
            token_type_ids=token_type_ids,
            position_ids=position_ids,
            head_mask=head_mask,
            inputs_embeds=inputs_embeds,
            encoder_hidden_states=encoder_hidden_states,
            encoder_attention_mask=encoder_attention_mask,
            past_key_values=past_key_values,
            use_cache=use_cache,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )

        sequence_output = outputs[0]
        prediction_scores = self.cls(sequence_output)

        lm_loss = None
        if labels is not None:
            # we are doing next-token prediction; shift prediction scores and input ids by one
            shifted_prediction_scores = prediction_scores[:, :-1, :]
            labels = labels[:, 1:]
            lm_loss = ops.cross_entropy(
                shifted_prediction_scores.view(-1, self.config.vocab_size),
                labels.view(-1),
            )

        if not return_dict:
            output = (prediction_scores,) + outputs[2:]
            return ((lm_loss,) + output) if lm_loss is not None else output

        return CausalLMOutputWithCrossAttentions(
            loss=lm_loss,
            logits=prediction_scores,
            past_key_values=outputs.past_key_values,
            hidden_states=outputs.hidden_states,
            attentions=outputs.attentions,
            cross_attentions=outputs.cross_attentions,
        )

    def prepare_inputs_for_generation(
        self,
        input_ids,
        input_shape_ids=None,
        input_pronunciation_ids=None,
        past_key_values=None,
        attention_mask=None,
        **model_kwargs,
    ):
        input_shape = input_ids.shape

        # if model is used as a decoder in encoder-decoder model, the decoder attention mask is created on the fly
        if attention_mask is None:
            attention_mask = input_ids.new_ones(input_shape)

        # cut decoder_input_ids if past_key_values is used
        if past_key_values is not None:
            past_length = past_key_values[0][0].shape[2]

            # Some generation methods already pass only the last input ID
            if input_ids.shape[1] > past_length:
                remove_prefix_length = past_length
            else:
                # Default to old behavior: keep only final ID
                remove_prefix_length = input_ids.shape[1] - 1

            input_ids = input_ids[:, remove_prefix_length:]
            if input_shape_ids is not None:
                input_shape_ids = input_shape_ids[:, -1:]
            if input_pronunciation_ids is not None:
                input_pronunciation_ids = input_pronunciation_ids[:, -1:]

        return {
            "input_ids": input_ids,
            "input_shape_ids": input_shape_ids,
            "input_pronunciation_ids": input_pronunciation_ids,
            "attention_mask": attention_mask,
            "past_key_values": past_key_values,
        }

    # Copied from transformers.models.bert.modeling_bert.BertLMHeadModel._reorder_cache
    def _reorder_cache(self, past_key_values, beam_idx):
        reordered_past = ()
        for layer_past in past_key_values:
            reordered_past += (
                tuple(
                    past_state.index_select(0, beam_idx) for past_state in layer_past
                ),
            )
        return reordered_past

mindnlp.transformers.models.roc_bert.modeling_roc_bert.RoCBertForCausalLM.forward(input_ids=None, input_shape_ids=None, input_pronunciation_ids=None, attention_mask=None, token_type_ids=None, position_ids=None, inputs_embeds=None, encoder_hidden_states=None, encoder_attention_mask=None, head_mask=None, past_key_values=None, labels=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None)

PARAMETER DESCRIPTION
encoder_hidden_states

Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if the model is configured as a decoder.

TYPE: (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional* DEFAULT: None

encoder_attention_mask

Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in the cross-attention if the model is configured as a decoder. Mask values selected in [0, 1]:

  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.

TYPE: `torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional* DEFAULT: None

past_key_values

Tuple of tuple(torch.FloatTensor) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)) and 2 additional tensors of shape (batch_size, num_heads, encoder_sequence_length, embed_size_per_head). The two additional tensors are only required when the model is used as a decoder in a Sequence to Sequence model.

Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.

If past_key_values are used, the user can optionally input only the last decoder_input_ids (those that don't have their past key value states given to this model) of shape (batch_size, 1) instead of all decoder_input_ids of shape (batch_size, sequence_length).

TYPE: `tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True` DEFAULT: None

labels

Labels for computing the left-to-right language modeling loss (next word prediction). Indices should be in [-100, 0, ..., config.vocab_size] (see input_ids docstring) Tokens with indices set to -100 are ignored (masked), the loss is only computed for the tokens with labels n [0, ..., config.vocab_size].

TYPE: `torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional* DEFAULT: None

use_cache

If set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values).

TYPE: `bool`, *optional* DEFAULT: None

RETURNS DESCRIPTION
Union[Tuple[Tensor], CausalLMOutputWithCrossAttentions]

Union[Tuple[mindspore.Tensor], CausalLMOutputWithCrossAttentions]
Example 
>>> from transformers import AutoTokenizer, RoCBertForCausalLM, RoCBertConfig
>>> import torch
...
>>> tokenizer = AutoTokenizer.from_pretrained("weiweishi/roc-bert-base-zh")
>>> config = RoCBertConfig.from_pretrained("weiweishi/roc-bert-base-zh")
>>> config.is_decoder = True
>>> model = RoCBertForCausalLM.from_pretrained("weiweishi/roc-bert-base-zh", config=config)
...
>>> inputs = tokenizer("你好，很高兴认识你", return_tensors="pt")
>>> outputs = model(**inputs)
...
>>> prediction_logits = outputs.logits
Source code in mindnlp/transformers/models/roc_bert/modeling_roc_bert.py 
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
def forward(
    self,
    input_ids: Optional[mindspore.Tensor] = None,
    input_shape_ids: Optional[mindspore.Tensor] = None,
    input_pronunciation_ids: Optional[mindspore.Tensor] = None,
    attention_mask: Optional[mindspore.Tensor] = None,
    token_type_ids: Optional[mindspore.Tensor] = None,
    position_ids: Optional[mindspore.Tensor] = None,
    inputs_embeds: Optional[mindspore.Tensor] = None,
    encoder_hidden_states: Optional[mindspore.Tensor] = None,
    encoder_attention_mask: Optional[mindspore.Tensor] = None,
    head_mask: Optional[mindspore.Tensor] = None,
    past_key_values: Optional[List[mindspore.Tensor]] = None,
    labels: Optional[mindspore.Tensor] = None,
    use_cache: Optional[bool] = None,
    output_attentions: Optional[bool] = None,
    output_hidden_states: Optional[bool] = None,
    return_dict: Optional[bool] = None,
) -> Union[Tuple[mindspore.Tensor], CausalLMOutputWithCrossAttentions]:
    r"""
    Args:
        encoder_hidden_states  (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
            Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if
            the model is configured as a decoder.
        encoder_attention_mask (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*):
            Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in
            the cross-attention if the model is configured as a decoder. Mask values selected in `[0, 1]`:

            - 1 for tokens that are **not masked**,
            - 0 for tokens that are **masked**.
        past_key_values (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
            Tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of shape
            `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and 2 additional tensors of shape
            `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`. The two additional tensors are
            only required when the model is used as a decoder in a Sequence to Sequence model.

            Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention
            blocks) that can be used (see `past_key_values` input) to speed up sequential decoding.

            If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those that
            don't have their past key value states given to this model) of shape `(batch_size, 1)` instead of all
            `decoder_input_ids` of shape `(batch_size, sequence_length)`.
        labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
            Labels for computing the left-to-right language modeling loss (next word prediction). Indices should be in
            `[-100, 0, ..., config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are
            ignored (masked), the loss is only computed for the tokens with labels n `[0, ..., config.vocab_size]`.
        use_cache (`bool`, *optional*):
            If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see
            `past_key_values`).

    Returns:
        `Union[Tuple[mindspore.Tensor], CausalLMOutputWithCrossAttentions]`

    Example:
        ```python
        >>> from transformers import AutoTokenizer, RoCBertForCausalLM, RoCBertConfig
        >>> import torch
        ...
        >>> tokenizer = AutoTokenizer.from_pretrained("weiweishi/roc-bert-base-zh")
        >>> config = RoCBertConfig.from_pretrained("weiweishi/roc-bert-base-zh")
        >>> config.is_decoder = True
        >>> model = RoCBertForCausalLM.from_pretrained("weiweishi/roc-bert-base-zh", config=config)
        ...
        >>> inputs = tokenizer("你好，很高兴认识你", return_tensors="pt")
        >>> outputs = model(**inputs)
        ...
        >>> prediction_logits = outputs.logits
        ```
    """
    return_dict = (
        return_dict if return_dict is not None else self.config.use_return_dict
    )

    outputs = self.roc_bert(
        input_ids,
        input_shape_ids=input_shape_ids,
        input_pronunciation_ids=input_pronunciation_ids,
        attention_mask=attention_mask,
        token_type_ids=token_type_ids,
        position_ids=position_ids,
        head_mask=head_mask,
        inputs_embeds=inputs_embeds,
        encoder_hidden_states=encoder_hidden_states,
        encoder_attention_mask=encoder_attention_mask,
        past_key_values=past_key_values,
        use_cache=use_cache,
        output_attentions=output_attentions,
        output_hidden_states=output_hidden_states,
        return_dict=return_dict,
    )

    sequence_output = outputs[0]
    prediction_scores = self.cls(sequence_output)

    lm_loss = None
    if labels is not None:
        # we are doing next-token prediction; shift prediction scores and input ids by one
        shifted_prediction_scores = prediction_scores[:, :-1, :]
        labels = labels[:, 1:]
        lm_loss = ops.cross_entropy(
            shifted_prediction_scores.view(-1, self.config.vocab_size),
            labels.view(-1),
        )

    if not return_dict:
        output = (prediction_scores,) + outputs[2:]
        return ((lm_loss,) + output) if lm_loss is not None else output

    return CausalLMOutputWithCrossAttentions(
        loss=lm_loss,
        logits=prediction_scores,
        past_key_values=outputs.past_key_values,
        hidden_states=outputs.hidden_states,
        attentions=outputs.attentions,
        cross_attentions=outputs.cross_attentions,
    )

mindnlp.transformers.models.roc_bert.modeling_roc_bert.RoCBertForMaskedLM

Bases: RoCBertPreTrainedModel

Source code in mindnlp/transformers/models/roc_bert/modeling_roc_bert.py 
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
class RoCBertForMaskedLM(RoCBertPreTrainedModel):
    _tied_weights_keys = [
        "cls.predictions.decoder.weight",
        "cls.predictions.decoder.bias",
    ]

    # Copied from transformers.models.bert.modeling_bert.BertForMaskedLM.__init__ with Bert->RoCBert,bert->roc_bert
    def __init__(self, config):
        super().__init__(config)

        if config.is_decoder:
            logger.warning(
                "If you want to use `RoCBertForMaskedLM` make sure `config.is_decoder=False` for "
                "bi-directional self-attention."
            )

        self.roc_bert = RoCBertModel(config, add_pooling_layer=False)
        self.cls = RoCBertOnlyMLMHead(config)

        # Initialize weights and apply final processing
        self.post_init()

    # Copied from transformers.models.bert.modeling_bert.BertForMaskedLM.get_output_embeddings
    def get_output_embeddings(self):
        return self.cls.predictions.decoder

    # Copied from transformers.models.bert.modeling_bert.BertForMaskedLM.set_output_embeddings
    def set_output_embeddings(self, new_embeddings):
        self.cls.predictions.decoder = new_embeddings
        self.cls.predictions.bias = new_embeddings.bias

    def forward(
        self,
        input_ids: Optional[mindspore.Tensor] = None,
        input_shape_ids: Optional[mindspore.Tensor] = None,
        input_pronunciation_ids: Optional[mindspore.Tensor] = None,
        attention_mask: Optional[mindspore.Tensor] = None,
        token_type_ids: Optional[mindspore.Tensor] = None,
        position_ids: Optional[mindspore.Tensor] = None,
        head_mask: Optional[mindspore.Tensor] = None,
        inputs_embeds: Optional[mindspore.Tensor] = None,
        encoder_hidden_states: Optional[mindspore.Tensor] = None,
        encoder_attention_mask: Optional[mindspore.Tensor] = None,
        labels: Optional[mindspore.Tensor] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
    ) -> Union[Tuple[mindspore.Tensor], MaskedLMOutput]:
        r"""
        Args:
            labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
                Labels for computing the masked language modeling loss. Indices should be in `[-100, 0, ...,
                config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are ignored (masked), the
                loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.

        Example:
            ```python
            >>> from transformers import AutoTokenizer, RoCBertForMaskedLM
            >>> import torch
            ...
            >>> tokenizer = AutoTokenizer.from_pretrained("weiweishi/roc-bert-base-zh")
            >>> model = RoCBertForMaskedLM.from_pretrained("weiweishi/roc-bert-base-zh")
            ...
            >>> inputs = tokenizer("法国是首都[MASK].", return_tensors="pt")
            ...
            >>> with torch.no_grad():
            ...     logits = model(**inputs).logits
            ...
            >>> # retrieve index of {mask}
            >>> mask_token_index = (inputs.input_ids == tokenizer.mask_token_id)[0].nonzero(as_tuple=True)[0]
            ...
            >>> predicted_token_id = logits[0, mask_token_index].argmax(axis=-1)
            >>> tokenizer.decode(predicted_token_id)
            '.'
            ```
        """
        return_dict = (
            return_dict if return_dict is not None else self.config.use_return_dict
        )

        outputs = self.roc_bert(
            input_ids,
            input_shape_ids=input_shape_ids,
            input_pronunciation_ids=input_pronunciation_ids,
            attention_mask=attention_mask,
            token_type_ids=token_type_ids,
            position_ids=position_ids,
            head_mask=head_mask,
            inputs_embeds=inputs_embeds,
            encoder_hidden_states=encoder_hidden_states,
            encoder_attention_mask=encoder_attention_mask,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )

        sequence_output = outputs[0]
        prediction_scores = self.cls(sequence_output)

        masked_lm_loss = None
        if labels is not None:
            masked_lm_loss = ops.cross_entropy(
                prediction_scores.view(-1, self.config.vocab_size), labels.view(-1)
            )

        if not return_dict:
            output = (prediction_scores,) + outputs[2:]
            return (
                ((masked_lm_loss,) + output) if masked_lm_loss is not None else output
            )

        return MaskedLMOutput(
            loss=masked_lm_loss,
            logits=prediction_scores,
            hidden_states=outputs.hidden_states,
            attentions=outputs.attentions,
        )

    def prepare_inputs_for_generation(
        self,
        input_ids,
        input_shape_ids=None,
        input_pronunciation_ids=None,
        attention_mask=None,
        **model_kwargs,
    ):
        input_shape = input_ids.shape
        effective_batch_size = input_shape[0]

        #  add a dummy token
        if self.config.pad_token_id is None:
            raise ValueError("The PAD token should be defined for generation")

        attention_mask = ops.cat(
            [attention_mask, attention_mask.new_zeros(attention_mask.shape[0], 1)],
            axis=-1,
        )
        dummy_token = ops.full(
            (effective_batch_size, 1), self.config.pad_token_id, dtype=mindspore.int64
        )
        input_ids = ops.cat([input_ids, dummy_token], axis=1)
        if input_shape_ids is not None:
            input_shape_ids = ops.cat([input_shape_ids, dummy_token], axis=1)
        if input_pronunciation_ids is not None:
            input_pronunciation_ids = ops.cat(
                [input_pronunciation_ids, dummy_token], axis=1
            )

        return {
            "input_ids": input_ids,
            "input_shape_ids": input_shape_ids,
            "input_pronunciation_ids": input_pronunciation_ids,
            "attention_mask": attention_mask,
        }

mindnlp.transformers.models.roc_bert.modeling_roc_bert.RoCBertForMaskedLM.forward(input_ids=None, input_shape_ids=None, input_pronunciation_ids=None, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, encoder_hidden_states=None, encoder_attention_mask=None, labels=None, output_attentions=None, output_hidden_states=None, return_dict=None)

PARAMETER DESCRIPTION
labels

Labels for computing the masked language modeling loss. Indices should be in [-100, 0, ..., config.vocab_size] (see input_ids docstring) Tokens with indices set to -100 are ignored (masked), the loss is only computed for the tokens with labels in [0, ..., config.vocab_size].

TYPE: `torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional* DEFAULT: None

Example 
>>> from transformers import AutoTokenizer, RoCBertForMaskedLM
>>> import torch
...
>>> tokenizer = AutoTokenizer.from_pretrained("weiweishi/roc-bert-base-zh")
>>> model = RoCBertForMaskedLM.from_pretrained("weiweishi/roc-bert-base-zh")
...
>>> inputs = tokenizer("法国是首都[MASK].", return_tensors="pt")
...
>>> with torch.no_grad():
...     logits = model(**inputs).logits
...
>>> # retrieve index of {mask}
>>> mask_token_index = (inputs.input_ids == tokenizer.mask_token_id)[0].nonzero(as_tuple=True)[0]
...
>>> predicted_token_id = logits[0, mask_token_index].argmax(axis=-1)
>>> tokenizer.decode(predicted_token_id)
'.'
Source code in mindnlp/transformers/models/roc_bert/modeling_roc_bert.py 
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
def forward(
    self,
    input_ids: Optional[mindspore.Tensor] = None,
    input_shape_ids: Optional[mindspore.Tensor] = None,
    input_pronunciation_ids: Optional[mindspore.Tensor] = None,
    attention_mask: Optional[mindspore.Tensor] = None,
    token_type_ids: Optional[mindspore.Tensor] = None,
    position_ids: Optional[mindspore.Tensor] = None,
    head_mask: Optional[mindspore.Tensor] = None,
    inputs_embeds: Optional[mindspore.Tensor] = None,
    encoder_hidden_states: Optional[mindspore.Tensor] = None,
    encoder_attention_mask: Optional[mindspore.Tensor] = None,
    labels: Optional[mindspore.Tensor] = None,
    output_attentions: Optional[bool] = None,
    output_hidden_states: Optional[bool] = None,
    return_dict: Optional[bool] = None,
) -> Union[Tuple[mindspore.Tensor], MaskedLMOutput]:
    r"""
    Args:
        labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
            Labels for computing the masked language modeling loss. Indices should be in `[-100, 0, ...,
            config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are ignored (masked), the
            loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.

    Example:
        ```python
        >>> from transformers import AutoTokenizer, RoCBertForMaskedLM
        >>> import torch
        ...
        >>> tokenizer = AutoTokenizer.from_pretrained("weiweishi/roc-bert-base-zh")
        >>> model = RoCBertForMaskedLM.from_pretrained("weiweishi/roc-bert-base-zh")
        ...
        >>> inputs = tokenizer("法国是首都[MASK].", return_tensors="pt")
        ...
        >>> with torch.no_grad():
        ...     logits = model(**inputs).logits
        ...
        >>> # retrieve index of {mask}
        >>> mask_token_index = (inputs.input_ids == tokenizer.mask_token_id)[0].nonzero(as_tuple=True)[0]
        ...
        >>> predicted_token_id = logits[0, mask_token_index].argmax(axis=-1)
        >>> tokenizer.decode(predicted_token_id)
        '.'
        ```
    """
    return_dict = (
        return_dict if return_dict is not None else self.config.use_return_dict
    )

    outputs = self.roc_bert(
        input_ids,
        input_shape_ids=input_shape_ids,
        input_pronunciation_ids=input_pronunciation_ids,
        attention_mask=attention_mask,
        token_type_ids=token_type_ids,
        position_ids=position_ids,
        head_mask=head_mask,
        inputs_embeds=inputs_embeds,
        encoder_hidden_states=encoder_hidden_states,
        encoder_attention_mask=encoder_attention_mask,
        output_attentions=output_attentions,
        output_hidden_states=output_hidden_states,
        return_dict=return_dict,
    )

    sequence_output = outputs[0]
    prediction_scores = self.cls(sequence_output)

    masked_lm_loss = None
    if labels is not None:
        masked_lm_loss = ops.cross_entropy(
            prediction_scores.view(-1, self.config.vocab_size), labels.view(-1)
        )

    if not return_dict:
        output = (prediction_scores,) + outputs[2:]
        return (
            ((masked_lm_loss,) + output) if masked_lm_loss is not None else output
        )

    return MaskedLMOutput(
        loss=masked_lm_loss,
        logits=prediction_scores,
        hidden_states=outputs.hidden_states,
        attentions=outputs.attentions,
    )

mindnlp.transformers.models.roc_bert.modeling_roc_bert.RoCBertForMultipleChoice

Bases: RoCBertPreTrainedModel

Source code in mindnlp/transformers/models/roc_bert/modeling_roc_bert.py 
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
class RoCBertForMultipleChoice(RoCBertPreTrainedModel):
    # Copied from transformers.models.bert.modeling_bert.BertForMultipleChoice.__init__ with Bert->RoCBert,bert->roc_bert
    def __init__(self, config):
        super().__init__(config)

        self.roc_bert = RoCBertModel(config)
        classifier_dropout = (
            config.classifier_dropout
            if config.classifier_dropout is not None
            else config.hidden_dropout_prob
        )
        self.dropout = nn.Dropout(p=classifier_dropout)
        self.classifier = nn.Linear(config.hidden_size, 1)

        # Initialize weights and apply final processing
        self.post_init()

    def forward(
        self,
        input_ids: Optional[mindspore.Tensor] = None,
        input_shape_ids: Optional[mindspore.Tensor] = None,
        input_pronunciation_ids: Optional[mindspore.Tensor] = None,
        attention_mask: Optional[mindspore.Tensor] = None,
        token_type_ids: Optional[mindspore.Tensor] = None,
        position_ids: Optional[mindspore.Tensor] = None,
        head_mask: Optional[mindspore.Tensor] = None,
        inputs_embeds: Optional[mindspore.Tensor] = None,
        labels: Optional[mindspore.Tensor] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
    ) -> Union[Tuple[mindspore.Tensor], MultipleChoiceModelOutput]:
        r"""
        Args:
            labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
                Labels for computing the multiple choice classification loss. Indices should be in `[0, ...,
                num_choices-1]` where `num_choices` is the size of the second dimension of the input tensors. (See
                `input_ids` above)
        """
        return_dict = (
            return_dict if return_dict is not None else self.config.use_return_dict
        )
        num_choices = (
            input_ids.shape[1] if input_ids is not None else inputs_embeds.shape[1]
        )

        input_ids = (
            input_ids.view(-1, input_ids.shape[-1]) if input_ids is not None else None
        )
        input_shape_ids = (
            input_shape_ids.view(-1, input_shape_ids.shape[-1])
            if input_shape_ids is not None
            else None
        )
        input_pronunciation_ids = (
            input_pronunciation_ids.view(-1, input_pronunciation_ids.shape[-1])
            if input_pronunciation_ids is not None
            else None
        )
        attention_mask = (
            attention_mask.view(-1, attention_mask.shape[-1])
            if attention_mask is not None
            else None
        )
        token_type_ids = (
            token_type_ids.view(-1, token_type_ids.shape[-1])
            if token_type_ids is not None
            else None
        )
        position_ids = (
            position_ids.view(-1, position_ids.shape[-1])
            if position_ids is not None
            else None
        )
        inputs_embeds = (
            inputs_embeds.view(-1, inputs_embeds.shape[-2], inputs_embeds.shape[-1])
            if inputs_embeds is not None
            else None
        )

        outputs = self.roc_bert(
            input_ids,
            input_shape_ids=input_shape_ids,
            input_pronunciation_ids=input_pronunciation_ids,
            attention_mask=attention_mask,
            token_type_ids=token_type_ids,
            position_ids=position_ids,
            head_mask=head_mask,
            inputs_embeds=inputs_embeds,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )

        pooled_output = outputs[1]

        pooled_output = self.dropout(pooled_output)
        logits = self.classifier(pooled_output)
        reshaped_logits = logits.view(-1, num_choices)

        loss = None
        if labels is not None:
            loss = ops.cross_entropy(reshaped_logits, labels)

        if not return_dict:
            output = (reshaped_logits,) + outputs[2:]
            return ((loss,) + output) if loss is not None else output

        return MultipleChoiceModelOutput(
            loss=loss,
            logits=reshaped_logits,
            hidden_states=outputs.hidden_states,
            attentions=outputs.attentions,
        )

mindnlp.transformers.models.roc_bert.modeling_roc_bert.RoCBertForMultipleChoice.forward(input_ids=None, input_shape_ids=None, input_pronunciation_ids=None, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, labels=None, output_attentions=None, output_hidden_states=None, return_dict=None)

PARAMETER DESCRIPTION
labels

Labels for computing the multiple choice classification loss. Indices should be in [0, ..., num_choices-1] where num_choices is the size of the second dimension of the input tensors. (See input_ids above)

TYPE: `torch.LongTensor` of shape `(batch_size,)`, *optional* DEFAULT: None

Source code in mindnlp/transformers/models/roc_bert/modeling_roc_bert.py 
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
def forward(
    self,
    input_ids: Optional[mindspore.Tensor] = None,
    input_shape_ids: Optional[mindspore.Tensor] = None,
    input_pronunciation_ids: Optional[mindspore.Tensor] = None,
    attention_mask: Optional[mindspore.Tensor] = None,
    token_type_ids: Optional[mindspore.Tensor] = None,
    position_ids: Optional[mindspore.Tensor] = None,
    head_mask: Optional[mindspore.Tensor] = None,
    inputs_embeds: Optional[mindspore.Tensor] = None,
    labels: Optional[mindspore.Tensor] = None,
    output_attentions: Optional[bool] = None,
    output_hidden_states: Optional[bool] = None,
    return_dict: Optional[bool] = None,
) -> Union[Tuple[mindspore.Tensor], MultipleChoiceModelOutput]:
    r"""
    Args:
        labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
            Labels for computing the multiple choice classification loss. Indices should be in `[0, ...,
            num_choices-1]` where `num_choices` is the size of the second dimension of the input tensors. (See
            `input_ids` above)
    """
    return_dict = (
        return_dict if return_dict is not None else self.config.use_return_dict
    )
    num_choices = (
        input_ids.shape[1] if input_ids is not None else inputs_embeds.shape[1]
    )

    input_ids = (
        input_ids.view(-1, input_ids.shape[-1]) if input_ids is not None else None
    )
    input_shape_ids = (
        input_shape_ids.view(-1, input_shape_ids.shape[-1])
        if input_shape_ids is not None
        else None
    )
    input_pronunciation_ids = (
        input_pronunciation_ids.view(-1, input_pronunciation_ids.shape[-1])
        if input_pronunciation_ids is not None
        else None
    )
    attention_mask = (
        attention_mask.view(-1, attention_mask.shape[-1])
        if attention_mask is not None
        else None
    )
    token_type_ids = (
        token_type_ids.view(-1, token_type_ids.shape[-1])
        if token_type_ids is not None
        else None
    )
    position_ids = (
        position_ids.view(-1, position_ids.shape[-1])
        if position_ids is not None
        else None
    )
    inputs_embeds = (
        inputs_embeds.view(-1, inputs_embeds.shape[-2], inputs_embeds.shape[-1])
        if inputs_embeds is not None
        else None
    )

    outputs = self.roc_bert(
        input_ids,
        input_shape_ids=input_shape_ids,
        input_pronunciation_ids=input_pronunciation_ids,
        attention_mask=attention_mask,
        token_type_ids=token_type_ids,
        position_ids=position_ids,
        head_mask=head_mask,
        inputs_embeds=inputs_embeds,
        output_attentions=output_attentions,
        output_hidden_states=output_hidden_states,
        return_dict=return_dict,
    )

    pooled_output = outputs[1]

    pooled_output = self.dropout(pooled_output)
    logits = self.classifier(pooled_output)
    reshaped_logits = logits.view(-1, num_choices)

    loss = None
    if labels is not None:
        loss = ops.cross_entropy(reshaped_logits, labels)

    if not return_dict:
        output = (reshaped_logits,) + outputs[2:]
        return ((loss,) + output) if loss is not None else output

    return MultipleChoiceModelOutput(
        loss=loss,
        logits=reshaped_logits,
        hidden_states=outputs.hidden_states,
        attentions=outputs.attentions,
    )

mindnlp.transformers.models.roc_bert.modeling_roc_bert.RoCBertForPreTraining

Bases: RoCBertPreTrainedModel

Source code in mindnlp/transformers/models/roc_bert/modeling_roc_bert.py 
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
class RoCBertForPreTraining(RoCBertPreTrainedModel):
    _tied_weights_keys = [
        "cls.predictions.decoder.weight",
        "cls.predictions.decoder.bias",
    ]

    def __init__(self, config):
        super().__init__(config)

        self.roc_bert = RoCBertModel(config)
        self.cls = RoCBertOnlyMLMHead(config)

        # Initialize weights and apply final processing
        self.post_init()

    # Copied from transformers.models.bert.modeling_bert.BertForPreTraining.get_output_embeddings
    def get_output_embeddings(self):
        return self.cls.predictions.decoder

    # Copied from transformers.models.bert.modeling_bert.BertForPreTraining.set_output_embeddings
    def set_output_embeddings(self, new_embeddings):
        self.cls.predictions.decoder = new_embeddings
        self.cls.predictions.bias = new_embeddings.bias

    def forward(
        self,
        input_ids: Optional[mindspore.Tensor] = None,
        input_shape_ids: Optional[mindspore.Tensor] = None,
        input_pronunciation_ids: Optional[mindspore.Tensor] = None,
        attention_mask: Optional[mindspore.Tensor] = None,
        token_type_ids: Optional[mindspore.Tensor] = None,
        attack_input_ids: Optional[mindspore.Tensor] = None,
        attack_input_shape_ids: Optional[mindspore.Tensor] = None,
        attack_input_pronunciation_ids: Optional[mindspore.Tensor] = None,
        attack_attention_mask: Optional[mindspore.Tensor] = None,
        attack_token_type_ids: Optional[mindspore.Tensor] = None,
        position_ids: Optional[mindspore.Tensor] = None,
        head_mask: Optional[mindspore.Tensor] = None,
        inputs_embeds: Optional[mindspore.Tensor] = None,
        labels_input_ids: Optional[mindspore.Tensor] = None,
        labels_input_shape_ids: Optional[mindspore.Tensor] = None,
        labels_input_pronunciation_ids: Optional[mindspore.Tensor] = None,
        labels_attention_mask: Optional[mindspore.Tensor] = None,
        labels_token_type_ids: Optional[mindspore.Tensor] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
        **kwargs,
    ) -> Union[Tuple[mindspore.Tensor], MaskedLMOutput]:
        r"""
        Args:
            attack_input_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
                attack sample ids for computing the contrastive loss. Indices should be in `[-100, 0, ...,
                config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are ignored (masked),
                the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`
            attack_input_shape_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
                attack sample shape ids for computing the contrastive loss. Indices should be in `[-100, 0, ...,
                config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are ignored (masked),
                the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`
            attack_input_pronunciation_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
                attack sample pronunciation ids for computing the contrastive loss. Indices should be in `[-100, 0,
                ..., config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are ignored
                (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`
            labels_input_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
                target ids for computing the contrastive loss and masked_lm_loss . Indices should be in `[-100, 0, ...,
                config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are ignored (masked),
                the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`
            labels_input_shape_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
                target shape ids for computing the contrastive loss and masked_lm_loss . Indices should be in `[-100,
                0, ..., config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are ignored
                (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`
            labels_input_pronunciation_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
                target pronunciation ids for computing the contrastive loss and masked_lm_loss . Indices should be in
                `[-100, 0, ..., config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are
                 ignored (masked), the loss is only computed for the tokens with labels in `[0, ...,
                 config.vocab_size]`

            kwargs (`Dict[str, any]`, optional, defaults to *{}*):
                Used to hide legacy arguments that have been deprecated.

        Returns:
            `Union[Tuple[mindspore.Tensor], MaskedLMOutput]`

        Example:
            ```python
            >>> from transformers import AutoTokenizer, RoCBertForPreTraining
            >>> import torch
            ...
            >>> tokenizer = AutoTokenizer.from_pretrained("weiweishi/roc-bert-base-zh")
            >>> model = RoCBertForPreTraining.from_pretrained("weiweishi/roc-bert-base-zh")
            ...
            >>> inputs = tokenizer("你好，很高兴认识你", return_tensors="pt")
            >>> attack_inputs = {}
            >>> for key in list(inputs.keys()):
            ...     attack_inputs[f"attack_{key}"] = inputs[key]
            >>> label_inputs = {}
            >>> for key in list(inputs.keys()):
            ...     label_inputs[f"labels_{key}"] = inputs[key]
            ...
            >>> inputs.update(label_inputs)
            >>> inputs.update(attack_inputs)
            >>> outputs = model(**inputs)
            ...
            >>> logits = outputs.logits
            >>> logits.shape
            torch.Size([1, 11, 21128])
            ```
        """
        return_dict = (
            return_dict if return_dict is not None else self.config.use_return_dict
        )

        outputs = self.roc_bert(
            input_ids,
            input_shape_ids=input_shape_ids,
            input_pronunciation_ids=input_pronunciation_ids,
            attention_mask=attention_mask,
            token_type_ids=token_type_ids,
            position_ids=position_ids,
            head_mask=head_mask,
            inputs_embeds=inputs_embeds,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )

        sequence_output, pooled_output = outputs[:2]
        prediction_scores = self.cls(sequence_output)

        loss = None
        if labels_input_ids is not None:
            # -100 index = padding token
            masked_lm_loss = ops.cross_entropy(
                prediction_scores.view(-1, self.config.vocab_size),
                labels_input_ids.view(-1),
            )

            if attack_input_ids is not None:
                batch_size, _ = labels_input_ids.shape

                target_inputs = labels_input_ids
                target_inputs[target_inputs == -100] = self.config.pad_token_id

                labels_output = self.roc_bert(
                    target_inputs,
                    input_shape_ids=labels_input_shape_ids,
                    input_pronunciation_ids=labels_input_pronunciation_ids,
                    attention_mask=labels_attention_mask,
                    token_type_ids=labels_token_type_ids,
                    return_dict=return_dict,
                )
                attack_output = self.roc_bert(
                    attack_input_ids,
                    input_shape_ids=attack_input_shape_ids,
                    input_pronunciation_ids=attack_input_pronunciation_ids,
                    attention_mask=attack_attention_mask,
                    token_type_ids=attack_token_type_ids,
                    return_dict=return_dict,
                )

                labels_pooled_output = labels_output[1]
                attack_pooled_output = attack_output[1]

                pooled_output_norm = ops.norm(pooled_output, dim=-1, keepdim=True)
                labels_pooled_output_norm = ops.norm(
                    labels_pooled_output, dim=-1, keepdim=True
                )
                attack_pooled_output_norm = ops.norm(
                    attack_pooled_output, dim=-1, keepdim=True
                )

                sim_matrix = ops.matmul(
                    pooled_output_norm, attack_pooled_output_norm.T
                )  # batch_size * hidden_dim
                sim_matrix_target = ops.matmul(
                    labels_pooled_output_norm, attack_pooled_output_norm.T
                )
                batch_labels = mindspore.Tensor(list(range(batch_size)))
                contrastive_loss = (
                    ops.cross_entropy(
                        100 * sim_matrix.view(batch_size, -1),
                        batch_labels.reshape(-1, 1),
                    )
                    + ops.cross_entropy(
                        100 * sim_matrix_target.view(batch_size, -1),
                        batch_labels.reshape(-1, 1),
                    )
                ) / 2

                loss = contrastive_loss + masked_lm_loss
            else:
                loss = masked_lm_loss

        if not return_dict:
            output = (prediction_scores,) + outputs[2:]
            return ((loss,) + output) if loss is not None else output

        return MaskedLMOutput(
            loss=loss,
            logits=prediction_scores,
            hidden_states=outputs.hidden_states,
            attentions=outputs.attentions,
        )

mindnlp.transformers.models.roc_bert.modeling_roc_bert.RoCBertForPreTraining.forward(input_ids=None, input_shape_ids=None, input_pronunciation_ids=None, attention_mask=None, token_type_ids=None, attack_input_ids=None, attack_input_shape_ids=None, attack_input_pronunciation_ids=None, attack_attention_mask=None, attack_token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, labels_input_ids=None, labels_input_shape_ids=None, labels_input_pronunciation_ids=None, labels_attention_mask=None, labels_token_type_ids=None, output_attentions=None, output_hidden_states=None, return_dict=None, **kwargs)

PARAMETER DESCRIPTION
attack_input_ids

attack sample ids for computing the contrastive loss. Indices should be in [-100, 0, ..., config.vocab_size] (see input_ids docstring) Tokens with indices set to -100 are ignored (masked), the loss is only computed for the tokens with labels in [0, ..., config.vocab_size]

TYPE: `torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional* DEFAULT: None

attack_input_shape_ids

attack sample shape ids for computing the contrastive loss. Indices should be in [-100, 0, ..., config.vocab_size] (see input_ids docstring) Tokens with indices set to -100 are ignored (masked), the loss is only computed for the tokens with labels in [0, ..., config.vocab_size]

TYPE: `torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional* DEFAULT: None

attack_input_pronunciation_ids

attack sample pronunciation ids for computing the contrastive loss. Indices should be in [-100, 0, ..., config.vocab_size] (see input_ids docstring) Tokens with indices set to -100 are ignored (masked), the loss is only computed for the tokens with labels in [0, ..., config.vocab_size]

TYPE: `torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional* DEFAULT: None

labels_input_ids

target ids for computing the contrastive loss and masked_lm_loss . Indices should be in [-100, 0, ..., config.vocab_size] (see input_ids docstring) Tokens with indices set to -100 are ignored (masked), the loss is only computed for the tokens with labels in [0, ..., config.vocab_size]

TYPE: `torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional* DEFAULT: None

labels_input_shape_ids

target shape ids for computing the contrastive loss and masked_lm_loss . Indices should be in [-100, 0, ..., config.vocab_size] (see input_ids docstring) Tokens with indices set to -100 are ignored (masked), the loss is only computed for the tokens with labels in [0, ..., config.vocab_size]

TYPE: `torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional* DEFAULT: None

labels_input_pronunciation_ids

target pronunciation ids for computing the contrastive loss and masked_lm_loss . Indices should be in [-100, 0, ..., config.vocab_size] (see input_ids docstring) Tokens with indices set to -100 are ignored (masked), the loss is only computed for the tokens with labels in [0, ..., config.vocab_size]

TYPE: `torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional* DEFAULT: None

kwargs

Used to hide legacy arguments that have been deprecated.

TYPE: `Dict[str, any]`, optional, defaults to *{}* DEFAULT: {}

RETURNS DESCRIPTION
Union[Tuple[Tensor], MaskedLMOutput]

Union[Tuple[mindspore.Tensor], MaskedLMOutput]
Example 
>>> from transformers import AutoTokenizer, RoCBertForPreTraining
>>> import torch
...
>>> tokenizer = AutoTokenizer.from_pretrained("weiweishi/roc-bert-base-zh")
>>> model = RoCBertForPreTraining.from_pretrained("weiweishi/roc-bert-base-zh")
...
>>> inputs = tokenizer("你好，很高兴认识你", return_tensors="pt")
>>> attack_inputs = {}
>>> for key in list(inputs.keys()):
...     attack_inputs[f"attack_{key}"] = inputs[key]
>>> label_inputs = {}
>>> for key in list(inputs.keys()):
...     label_inputs[f"labels_{key}"] = inputs[key]
...
>>> inputs.update(label_inputs)
>>> inputs.update(attack_inputs)
>>> outputs = model(**inputs)
...
>>> logits = outputs.logits
>>> logits.shape
torch.Size([1, 11, 21128])
Source code in mindnlp/transformers/models/roc_bert/modeling_roc_bert.py 
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
def forward(
    self,
    input_ids: Optional[mindspore.Tensor] = None,
    input_shape_ids: Optional[mindspore.Tensor] = None,
    input_pronunciation_ids: Optional[mindspore.Tensor] = None,
    attention_mask: Optional[mindspore.Tensor] = None,
    token_type_ids: Optional[mindspore.Tensor] = None,
    attack_input_ids: Optional[mindspore.Tensor] = None,
    attack_input_shape_ids: Optional[mindspore.Tensor] = None,
    attack_input_pronunciation_ids: Optional[mindspore.Tensor] = None,
    attack_attention_mask: Optional[mindspore.Tensor] = None,
    attack_token_type_ids: Optional[mindspore.Tensor] = None,
    position_ids: Optional[mindspore.Tensor] = None,
    head_mask: Optional[mindspore.Tensor] = None,
    inputs_embeds: Optional[mindspore.Tensor] = None,
    labels_input_ids: Optional[mindspore.Tensor] = None,
    labels_input_shape_ids: Optional[mindspore.Tensor] = None,
    labels_input_pronunciation_ids: Optional[mindspore.Tensor] = None,
    labels_attention_mask: Optional[mindspore.Tensor] = None,
    labels_token_type_ids: Optional[mindspore.Tensor] = None,
    output_attentions: Optional[bool] = None,
    output_hidden_states: Optional[bool] = None,
    return_dict: Optional[bool] = None,
    **kwargs,
) -> Union[Tuple[mindspore.Tensor], MaskedLMOutput]:
    r"""
    Args:
        attack_input_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
            attack sample ids for computing the contrastive loss. Indices should be in `[-100, 0, ...,
            config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are ignored (masked),
            the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`
        attack_input_shape_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
            attack sample shape ids for computing the contrastive loss. Indices should be in `[-100, 0, ...,
            config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are ignored (masked),
            the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`
        attack_input_pronunciation_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
            attack sample pronunciation ids for computing the contrastive loss. Indices should be in `[-100, 0,
            ..., config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are ignored
            (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`
        labels_input_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
            target ids for computing the contrastive loss and masked_lm_loss . Indices should be in `[-100, 0, ...,
            config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are ignored (masked),
            the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`
        labels_input_shape_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
            target shape ids for computing the contrastive loss and masked_lm_loss . Indices should be in `[-100,
            0, ..., config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are ignored
            (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`
        labels_input_pronunciation_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
            target pronunciation ids for computing the contrastive loss and masked_lm_loss . Indices should be in
            `[-100, 0, ..., config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are
             ignored (masked), the loss is only computed for the tokens with labels in `[0, ...,
             config.vocab_size]`

        kwargs (`Dict[str, any]`, optional, defaults to *{}*):
            Used to hide legacy arguments that have been deprecated.

    Returns:
        `Union[Tuple[mindspore.Tensor], MaskedLMOutput]`

    Example:
        ```python
        >>> from transformers import AutoTokenizer, RoCBertForPreTraining
        >>> import torch
        ...
        >>> tokenizer = AutoTokenizer.from_pretrained("weiweishi/roc-bert-base-zh")
        >>> model = RoCBertForPreTraining.from_pretrained("weiweishi/roc-bert-base-zh")
        ...
        >>> inputs = tokenizer("你好，很高兴认识你", return_tensors="pt")
        >>> attack_inputs = {}
        >>> for key in list(inputs.keys()):
        ...     attack_inputs[f"attack_{key}"] = inputs[key]
        >>> label_inputs = {}
        >>> for key in list(inputs.keys()):
        ...     label_inputs[f"labels_{key}"] = inputs[key]
        ...
        >>> inputs.update(label_inputs)
        >>> inputs.update(attack_inputs)
        >>> outputs = model(**inputs)
        ...
        >>> logits = outputs.logits
        >>> logits.shape
        torch.Size([1, 11, 21128])
        ```
    """
    return_dict = (
        return_dict if return_dict is not None else self.config.use_return_dict
    )

    outputs = self.roc_bert(
        input_ids,
        input_shape_ids=input_shape_ids,
        input_pronunciation_ids=input_pronunciation_ids,
        attention_mask=attention_mask,
        token_type_ids=token_type_ids,
        position_ids=position_ids,
        head_mask=head_mask,
        inputs_embeds=inputs_embeds,
        output_attentions=output_attentions,
        output_hidden_states=output_hidden_states,
        return_dict=return_dict,
    )

    sequence_output, pooled_output = outputs[:2]
    prediction_scores = self.cls(sequence_output)

    loss = None
    if labels_input_ids is not None:
        # -100 index = padding token
        masked_lm_loss = ops.cross_entropy(
            prediction_scores.view(-1, self.config.vocab_size),
            labels_input_ids.view(-1),
        )

        if attack_input_ids is not None:
            batch_size, _ = labels_input_ids.shape

            target_inputs = labels_input_ids
            target_inputs[target_inputs == -100] = self.config.pad_token_id

            labels_output = self.roc_bert(
                target_inputs,
                input_shape_ids=labels_input_shape_ids,
                input_pronunciation_ids=labels_input_pronunciation_ids,
                attention_mask=labels_attention_mask,
                token_type_ids=labels_token_type_ids,
                return_dict=return_dict,
            )
            attack_output = self.roc_bert(
                attack_input_ids,
                input_shape_ids=attack_input_shape_ids,
                input_pronunciation_ids=attack_input_pronunciation_ids,
                attention_mask=attack_attention_mask,
                token_type_ids=attack_token_type_ids,
                return_dict=return_dict,
            )

            labels_pooled_output = labels_output[1]
            attack_pooled_output = attack_output[1]

            pooled_output_norm = ops.norm(pooled_output, dim=-1, keepdim=True)
            labels_pooled_output_norm = ops.norm(
                labels_pooled_output, dim=-1, keepdim=True
            )
            attack_pooled_output_norm = ops.norm(
                attack_pooled_output, dim=-1, keepdim=True
            )

            sim_matrix = ops.matmul(
                pooled_output_norm, attack_pooled_output_norm.T
            )  # batch_size * hidden_dim
            sim_matrix_target = ops.matmul(
                labels_pooled_output_norm, attack_pooled_output_norm.T
            )
            batch_labels = mindspore.Tensor(list(range(batch_size)))
            contrastive_loss = (
                ops.cross_entropy(
                    100 * sim_matrix.view(batch_size, -1),
                    batch_labels.reshape(-1, 1),
                )
                + ops.cross_entropy(
                    100 * sim_matrix_target.view(batch_size, -1),
                    batch_labels.reshape(-1, 1),
                )
            ) / 2

            loss = contrastive_loss + masked_lm_loss
        else:
            loss = masked_lm_loss

    if not return_dict:
        output = (prediction_scores,) + outputs[2:]
        return ((loss,) + output) if loss is not None else output

    return MaskedLMOutput(
        loss=loss,
        logits=prediction_scores,
        hidden_states=outputs.hidden_states,
        attentions=outputs.attentions,
    )

mindnlp.transformers.models.roc_bert.modeling_roc_bert.RoCBertForQuestionAnswering

Bases: RoCBertPreTrainedModel

Source code in mindnlp/transformers/models/roc_bert/modeling_roc_bert.py 
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
class RoCBertForQuestionAnswering(RoCBertPreTrainedModel):
    # Copied from transformers.models.bert.modeling_bert.BertForQuestionAnswering.__init__ with Bert->RoCBert,bert->roc_bert
    def __init__(self, config):
        super().__init__(config)
        self.num_labels = config.num_labels

        self.roc_bert = RoCBertModel(config, add_pooling_layer=False)
        self.qa_outputs = nn.Linear(config.hidden_size, config.num_labels)

        # Initialize weights and apply final processing
        self.post_init()

    def forward(
        self,
        input_ids: Optional[mindspore.Tensor] = None,
        input_shape_ids: Optional[mindspore.Tensor] = None,
        input_pronunciation_ids: Optional[mindspore.Tensor] = None,
        attention_mask: Optional[mindspore.Tensor] = None,
        token_type_ids: Optional[mindspore.Tensor] = None,
        position_ids: Optional[mindspore.Tensor] = None,
        head_mask: Optional[mindspore.Tensor] = None,
        inputs_embeds: Optional[mindspore.Tensor] = None,
        start_positions: Optional[mindspore.Tensor] = None,
        end_positions: Optional[mindspore.Tensor] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
    ) -> Union[Tuple[mindspore.Tensor], QuestionAnsweringModelOutput]:
        r"""
        Args:
            start_positions (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
                Labels for position (index) of the start of the labelled span for computing the token classification loss.
                Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence
                are not taken into account for computing the loss.
            end_positions (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
                Labels for position (index) of the end of the labelled span for computing the token classification loss.
                Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence
                are not taken into account for computing the loss.
        """
        return_dict = (
            return_dict if return_dict is not None else self.config.use_return_dict
        )

        outputs = self.roc_bert(
            input_ids,
            input_shape_ids=input_shape_ids,
            input_pronunciation_ids=input_pronunciation_ids,
            attention_mask=attention_mask,
            token_type_ids=token_type_ids,
            position_ids=position_ids,
            head_mask=head_mask,
            inputs_embeds=inputs_embeds,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )

        sequence_output = outputs[0]

        logits = self.qa_outputs(sequence_output)
        start_logits, end_logits = logits.split(1, axis=-1)
        start_logits = start_logits.squeeze(-1)
        end_logits = end_logits.squeeze(-1)

        total_loss = None
        if start_positions is not None and end_positions is not None:
            # If we are on multi-GPU, split add a dimension
            if len(start_positions.shape) > 1:
                start_positions = start_positions.squeeze(-1)
            if len(end_positions.shape) > 1:
                end_positions = end_positions.squeeze(-1)
            # sometimes the start/end positions are outside our model inputs, we ignore these terms
            ignored_index = start_logits.shape[1]
            start_positions = start_positions.clamp(0, ignored_index)
            end_positions = end_positions.clamp(0, ignored_index)

            start_loss = ops.cross_entropy(
                start_logits, start_positions, ignore_index=ignored_index
            )
            end_loss = ops.cross_entropy(
                end_logits, end_positions, ignore_index=ignored_index
            )
            total_loss = (start_loss + end_loss) / 2

        if not return_dict:
            output = (start_logits, end_logits) + outputs[2:]
            return ((total_loss,) + output) if total_loss is not None else output

        return QuestionAnsweringModelOutput(
            loss=total_loss,
            start_logits=start_logits,
            end_logits=end_logits,
            hidden_states=outputs.hidden_states,
            attentions=outputs.attentions,
        )

mindnlp.transformers.models.roc_bert.modeling_roc_bert.RoCBertForQuestionAnswering.forward(input_ids=None, input_shape_ids=None, input_pronunciation_ids=None, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, start_positions=None, end_positions=None, output_attentions=None, output_hidden_states=None, return_dict=None)

PARAMETER DESCRIPTION
start_positions

Labels for position (index) of the start of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (sequence_length). Position outside of the sequence are not taken into account for computing the loss.

TYPE: `torch.LongTensor` of shape `(batch_size,)`, *optional* DEFAULT: None

end_positions

Labels for position (index) of the end of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (sequence_length). Position outside of the sequence are not taken into account for computing the loss.

TYPE: `torch.LongTensor` of shape `(batch_size,)`, *optional* DEFAULT: None

Source code in mindnlp/transformers/models/roc_bert/modeling_roc_bert.py 
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
def forward(
    self,
    input_ids: Optional[mindspore.Tensor] = None,
    input_shape_ids: Optional[mindspore.Tensor] = None,
    input_pronunciation_ids: Optional[mindspore.Tensor] = None,
    attention_mask: Optional[mindspore.Tensor] = None,
    token_type_ids: Optional[mindspore.Tensor] = None,
    position_ids: Optional[mindspore.Tensor] = None,
    head_mask: Optional[mindspore.Tensor] = None,
    inputs_embeds: Optional[mindspore.Tensor] = None,
    start_positions: Optional[mindspore.Tensor] = None,
    end_positions: Optional[mindspore.Tensor] = None,
    output_attentions: Optional[bool] = None,
    output_hidden_states: Optional[bool] = None,
    return_dict: Optional[bool] = None,
) -> Union[Tuple[mindspore.Tensor], QuestionAnsweringModelOutput]:
    r"""
    Args:
        start_positions (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
            Labels for position (index) of the start of the labelled span for computing the token classification loss.
            Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence
            are not taken into account for computing the loss.
        end_positions (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
            Labels for position (index) of the end of the labelled span for computing the token classification loss.
            Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence
            are not taken into account for computing the loss.
    """
    return_dict = (
        return_dict if return_dict is not None else self.config.use_return_dict
    )

    outputs = self.roc_bert(
        input_ids,
        input_shape_ids=input_shape_ids,
        input_pronunciation_ids=input_pronunciation_ids,
        attention_mask=attention_mask,
        token_type_ids=token_type_ids,
        position_ids=position_ids,
        head_mask=head_mask,
        inputs_embeds=inputs_embeds,
        output_attentions=output_attentions,
        output_hidden_states=output_hidden_states,
        return_dict=return_dict,
    )

    sequence_output = outputs[0]

    logits = self.qa_outputs(sequence_output)
    start_logits, end_logits = logits.split(1, axis=-1)
    start_logits = start_logits.squeeze(-1)
    end_logits = end_logits.squeeze(-1)

    total_loss = None
    if start_positions is not None and end_positions is not None:
        # If we are on multi-GPU, split add a dimension
        if len(start_positions.shape) > 1:
            start_positions = start_positions.squeeze(-1)
        if len(end_positions.shape) > 1:
            end_positions = end_positions.squeeze(-1)
        # sometimes the start/end positions are outside our model inputs, we ignore these terms
        ignored_index = start_logits.shape[1]
        start_positions = start_positions.clamp(0, ignored_index)
        end_positions = end_positions.clamp(0, ignored_index)

        start_loss = ops.cross_entropy(
            start_logits, start_positions, ignore_index=ignored_index
        )
        end_loss = ops.cross_entropy(
            end_logits, end_positions, ignore_index=ignored_index
        )
        total_loss = (start_loss + end_loss) / 2

    if not return_dict:
        output = (start_logits, end_logits) + outputs[2:]
        return ((total_loss,) + output) if total_loss is not None else output

    return QuestionAnsweringModelOutput(
        loss=total_loss,
        start_logits=start_logits,
        end_logits=end_logits,
        hidden_states=outputs.hidden_states,
        attentions=outputs.attentions,
    )

mindnlp.transformers.models.roc_bert.modeling_roc_bert.RoCBertForSequenceClassification

Bases: RoCBertPreTrainedModel

Source code in mindnlp/transformers/models/roc_bert/modeling_roc_bert.py 
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
class RoCBertForSequenceClassification(RoCBertPreTrainedModel):
    # Copied from transformers.models.bert.modeling_bert.BertForSequenceClassification.__init__ with Bert->RoCBert,bert->roc_bert
    def __init__(self, config):
        super().__init__(config)
        self.num_labels = config.num_labels
        self.config = config

        self.roc_bert = RoCBertModel(config)
        classifier_dropout = (
            config.classifier_dropout
            if config.classifier_dropout is not None
            else config.hidden_dropout_prob
        )
        self.dropout = nn.Dropout(classifier_dropout)
        self.classifier = nn.Linear(config.hidden_size, config.num_labels)

        # Initialize weights and apply final processing
        self.post_init()

    def forward(
        self,
        input_ids: Optional[mindspore.Tensor] = None,
        input_shape_ids: Optional[mindspore.Tensor] = None,
        input_pronunciation_ids: Optional[mindspore.Tensor] = None,
        attention_mask: Optional[mindspore.Tensor] = None,
        token_type_ids: Optional[mindspore.Tensor] = None,
        position_ids: Optional[mindspore.Tensor] = None,
        head_mask: Optional[mindspore.Tensor] = None,
        inputs_embeds: Optional[mindspore.Tensor] = None,
        labels: Optional[mindspore.Tensor] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
    ) -> Union[Tuple[mindspore.Tensor], SequenceClassifierOutput]:
        r"""
        Args:
            labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
                Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
                config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
                `config.num_labels > 1` a classification loss is computed (Cross-Entropy).
        """
        return_dict = (
            return_dict if return_dict is not None else self.config.use_return_dict
        )

        outputs = self.roc_bert(
            input_ids,
            input_shape_ids=input_shape_ids,
            input_pronunciation_ids=input_pronunciation_ids,
            attention_mask=attention_mask,
            token_type_ids=token_type_ids,
            position_ids=position_ids,
            head_mask=head_mask,
            inputs_embeds=inputs_embeds,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )

        pooled_output = outputs[1]

        pooled_output = self.dropout(pooled_output)
        logits = self.classifier(pooled_output)

        loss = None
        if labels is not None:
            if self.config.problem_type is None:
                if self.num_labels == 1:
                    self.config.problem_type = "regression"
                elif self.num_labels > 1 and labels.dtype in (
                    mindspore.int32,
                    mindspore.int64,
                ):
                    self.config.problem_type = "single_label_classification"
                else:
                    self.config.problem_type = "multi_label_classification"

            if self.config.problem_type == "regression":
                if self.num_labels == 1:
                    loss = ops.mse_loss(logits.squeeze(), labels.squeeze())
                else:
                    loss = ops.mse_loss(logits, labels)
            elif self.config.problem_type == "single_label_classification":
                loss = ops.cross_entropy(
                    logits.view(-1, self.num_labels), labels.view(-1)
                )
            elif self.config.problem_type == "multi_label_classification":
                loss = ops.binary_cross_entropy_with_logits(logits, labels)
        if not return_dict:
            output = (logits,) + outputs[2:]
            return ((loss,) + output) if loss is not None else output

        return SequenceClassifierOutput(
            loss=loss,
            logits=logits,
            hidden_states=outputs.hidden_states,
            attentions=outputs.attentions,
        )

mindnlp.transformers.models.roc_bert.modeling_roc_bert.RoCBertForSequenceClassification.forward(input_ids=None, input_shape_ids=None, input_pronunciation_ids=None, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, labels=None, output_attentions=None, output_hidden_states=None, return_dict=None)

PARAMETER DESCRIPTION
labels

Labels for computing the sequence classification/regression loss. Indices should be in [0, ..., config.num_labels - 1]. If config.num_labels == 1 a regression loss is computed (Mean-Square loss), If config.num_labels > 1 a classification loss is computed (Cross-Entropy).

TYPE: `torch.LongTensor` of shape `(batch_size,)`, *optional* DEFAULT: None

Source code in mindnlp/transformers/models/roc_bert/modeling_roc_bert.py 
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
def forward(
    self,
    input_ids: Optional[mindspore.Tensor] = None,
    input_shape_ids: Optional[mindspore.Tensor] = None,
    input_pronunciation_ids: Optional[mindspore.Tensor] = None,
    attention_mask: Optional[mindspore.Tensor] = None,
    token_type_ids: Optional[mindspore.Tensor] = None,
    position_ids: Optional[mindspore.Tensor] = None,
    head_mask: Optional[mindspore.Tensor] = None,
    inputs_embeds: Optional[mindspore.Tensor] = None,
    labels: Optional[mindspore.Tensor] = None,
    output_attentions: Optional[bool] = None,
    output_hidden_states: Optional[bool] = None,
    return_dict: Optional[bool] = None,
) -> Union[Tuple[mindspore.Tensor], SequenceClassifierOutput]:
    r"""
    Args:
        labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
            Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
            config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
            `config.num_labels > 1` a classification loss is computed (Cross-Entropy).
    """
    return_dict = (
        return_dict if return_dict is not None else self.config.use_return_dict
    )

    outputs = self.roc_bert(
        input_ids,
        input_shape_ids=input_shape_ids,
        input_pronunciation_ids=input_pronunciation_ids,
        attention_mask=attention_mask,
        token_type_ids=token_type_ids,
        position_ids=position_ids,
        head_mask=head_mask,
        inputs_embeds=inputs_embeds,
        output_attentions=output_attentions,
        output_hidden_states=output_hidden_states,
        return_dict=return_dict,
    )

    pooled_output = outputs[1]

    pooled_output = self.dropout(pooled_output)
    logits = self.classifier(pooled_output)

    loss = None
    if labels is not None:
        if self.config.problem_type is None:
            if self.num_labels == 1:
                self.config.problem_type = "regression"
            elif self.num_labels > 1 and labels.dtype in (
                mindspore.int32,
                mindspore.int64,
            ):
                self.config.problem_type = "single_label_classification"
            else:
                self.config.problem_type = "multi_label_classification"

        if self.config.problem_type == "regression":
            if self.num_labels == 1:
                loss = ops.mse_loss(logits.squeeze(), labels.squeeze())
            else:
                loss = ops.mse_loss(logits, labels)
        elif self.config.problem_type == "single_label_classification":
            loss = ops.cross_entropy(
                logits.view(-1, self.num_labels), labels.view(-1)
            )
        elif self.config.problem_type == "multi_label_classification":
            loss = ops.binary_cross_entropy_with_logits(logits, labels)
    if not return_dict:
        output = (logits,) + outputs[2:]
        return ((loss,) + output) if loss is not None else output

    return SequenceClassifierOutput(
        loss=loss,
        logits=logits,
        hidden_states=outputs.hidden_states,
        attentions=outputs.attentions,
    )

mindnlp.transformers.models.roc_bert.modeling_roc_bert.RoCBertForTokenClassification

Bases: RoCBertPreTrainedModel

Source code in mindnlp/transformers/models/roc_bert/modeling_roc_bert.py 
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
class RoCBertForTokenClassification(RoCBertPreTrainedModel):
    # Copied from transformers.models.bert.modeling_bert.BertForTokenClassification.__init__ with Bert->RoCBert,bert->roc_bert
    def __init__(self, config):
        super().__init__(config)
        self.num_labels = config.num_labels

        self.roc_bert = RoCBertModel(config, add_pooling_layer=False)
        classifier_dropout = (
            config.classifier_dropout
            if config.classifier_dropout is not None
            else config.hidden_dropout_prob
        )
        self.dropout = nn.Dropout(p=classifier_dropout)
        self.classifier = nn.Linear(config.hidden_size, config.num_labels)

        # Initialize weights and apply final processing
        self.post_init()

    def forward(
        self,
        input_ids: Optional[mindspore.Tensor] = None,
        input_shape_ids: Optional[mindspore.Tensor] = None,
        input_pronunciation_ids: Optional[mindspore.Tensor] = None,
        attention_mask: Optional[mindspore.Tensor] = None,
        token_type_ids: Optional[mindspore.Tensor] = None,
        position_ids: Optional[mindspore.Tensor] = None,
        head_mask: Optional[mindspore.Tensor] = None,
        inputs_embeds: Optional[mindspore.Tensor] = None,
        labels: Optional[mindspore.Tensor] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
    ) -> Union[Tuple, TokenClassifierOutput]:
        r"""
        Args:
            labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
                Labels for computing the token classification loss. Indices should be in `[0, ..., config.num_labels - 1]`.
        """
        return_dict = (
            return_dict if return_dict is not None else self.config.use_return_dict
        )

        outputs = self.roc_bert(
            input_ids,
            input_shape_ids=input_shape_ids,
            input_pronunciation_ids=input_pronunciation_ids,
            attention_mask=attention_mask,
            token_type_ids=token_type_ids,
            position_ids=position_ids,
            head_mask=head_mask,
            inputs_embeds=inputs_embeds,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )

        sequence_output = outputs[0]

        sequence_output = self.dropout(sequence_output)
        logits = self.classifier(sequence_output)

        loss = None
        if labels is not None:
            loss = ops.cross_entropy(logits.view(-1, self.num_labels), labels.view(-1))

        if not return_dict:
            output = (logits,) + outputs[2:]
            return ((loss,) + output) if loss is not None else output

        return TokenClassifierOutput(
            loss=loss,
            logits=logits,
            hidden_states=outputs.hidden_states,
            attentions=outputs.attentions,
        )

mindnlp.transformers.models.roc_bert.modeling_roc_bert.RoCBertForTokenClassification.forward(input_ids=None, input_shape_ids=None, input_pronunciation_ids=None, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, labels=None, output_attentions=None, output_hidden_states=None, return_dict=None)

PARAMETER DESCRIPTION
labels

Labels for computing the token classification loss. Indices should be in [0, ..., config.num_labels - 1].

TYPE: `torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional* DEFAULT: None

Source code in mindnlp/transformers/models/roc_bert/modeling_roc_bert.py 
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
def forward(
    self,
    input_ids: Optional[mindspore.Tensor] = None,
    input_shape_ids: Optional[mindspore.Tensor] = None,
    input_pronunciation_ids: Optional[mindspore.Tensor] = None,
    attention_mask: Optional[mindspore.Tensor] = None,
    token_type_ids: Optional[mindspore.Tensor] = None,
    position_ids: Optional[mindspore.Tensor] = None,
    head_mask: Optional[mindspore.Tensor] = None,
    inputs_embeds: Optional[mindspore.Tensor] = None,
    labels: Optional[mindspore.Tensor] = None,
    output_attentions: Optional[bool] = None,
    output_hidden_states: Optional[bool] = None,
    return_dict: Optional[bool] = None,
) -> Union[Tuple, TokenClassifierOutput]:
    r"""
    Args:
        labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
            Labels for computing the token classification loss. Indices should be in `[0, ..., config.num_labels - 1]`.
    """
    return_dict = (
        return_dict if return_dict is not None else self.config.use_return_dict
    )

    outputs = self.roc_bert(
        input_ids,
        input_shape_ids=input_shape_ids,
        input_pronunciation_ids=input_pronunciation_ids,
        attention_mask=attention_mask,
        token_type_ids=token_type_ids,
        position_ids=position_ids,
        head_mask=head_mask,
        inputs_embeds=inputs_embeds,
        output_attentions=output_attentions,
        output_hidden_states=output_hidden_states,
        return_dict=return_dict,
    )

    sequence_output = outputs[0]

    sequence_output = self.dropout(sequence_output)
    logits = self.classifier(sequence_output)

    loss = None
    if labels is not None:
        loss = ops.cross_entropy(logits.view(-1, self.num_labels), labels.view(-1))

    if not return_dict:
        output = (logits,) + outputs[2:]
        return ((loss,) + output) if loss is not None else output

    return TokenClassifierOutput(
        loss=loss,
        logits=logits,
        hidden_states=outputs.hidden_states,
        attentions=outputs.attentions,
    )

mindnlp.transformers.models.roc_bert.modeling_roc_bert.RoCBertModel

Bases: RoCBertPreTrainedModel

The model can behave as an encoder (with only self-attention) as well as a decoder, in which case a layer of cross-attention is added between the self-attention layers, following the architecture described in Attention is all you need by Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser and Illia Polosukhin.

To behave as an decoder the model needs to be initialized with the is_decoder argument of the configuration set to True. To be used in a Seq2Seq model, the model needs to be initialized with both is_decoder argument and add_cross_attention set to True; an encoder_hidden_states is then expected as an input to the forward pass.

Source code in mindnlp/transformers/models/roc_bert/modeling_roc_bert.py 
 820
 821
 822
 823
 824
 825
 826
 827
 828
 829
 830
 831
 832
 833
 834
 835
 836
 837
 838
 839
 840
 841
 842
 843
 844
 845
 846
 847
 848
 849
 850
 851
 852
 853
 854
 855
 856
 857
 858
 859
 860
 861
 862
 863
 864
 865
 866
 867
 868
 869
 870
 871
 872
 873
 874
 875
 876
 877
 878
 879
 880
 881
 882
 883
 884
 885
 886
 887
 888
 889
 890
 891
 892
 893
 894
 895
 896
 897
 898
 899
 900
 901
 902
 903
 904
 905
 906
 907
 908
 909
 910
 911
 912
 913
 914
 915
 916
 917
 918
 919
 920
 921
 922
 923
 924
 925
 926
 927
 928
 929
 930
 931
 932
 933
 934
 935
 936
 937
 938
 939
 940
 941
 942
 943
 944
 945
 946
 947
 948
 949
 950
 951
 952
 953
 954
 955
 956
 957
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
class RoCBertModel(RoCBertPreTrainedModel):
    """
    The model can behave as an encoder (with only self-attention) as well as a decoder, in which case a layer of
    cross-attention is added between the self-attention layers, following the architecture described in [Attention is
    all you need](https://arxiv.org/abs/1706.03762) by Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit,
    Llion Jones, Aidan N. Gomez, Lukasz Kaiser and Illia Polosukhin.

    To behave as an decoder the model needs to be initialized with the `is_decoder` argument of the configuration set
    to `True`. To be used in a Seq2Seq model, the model needs to be initialized with both `is_decoder` argument and
    `add_cross_attention` set to `True`; an `encoder_hidden_states` is then expected as an input to the forward pass.
    """

    # Copied from transformers.models.clap.modeling_clap.ClapTextModel.__init__ with ClapText->RoCBert
    def __init__(self, config, add_pooling_layer=True):
        super().__init__(config)
        self.config = config

        self.embeddings = RoCBertEmbeddings(config)
        self.encoder = RoCBertEncoder(config)

        self.pooler = RoCBertPooler(config) if add_pooling_layer else None

        # Initialize weights and apply final processing
        self.post_init()

    # Copied from transformers.models.bert.modeling_bert.BertModel.get_input_embeddings
    def get_input_embeddings(self):
        return self.embeddings.word_embeddings

    # Copied from transformers.models.bert.modeling_bert.BertModel.set_input_embeddings
    def set_input_embeddings(self, value):
        self.embeddings.word_embeddings = value

    def get_pronunciation_embeddings(self):
        return self.embeddings.pronunciation_embed

    def set_pronunciation_embeddings(self, value):
        self.embeddings.pronunciation_embed = value

    def get_shape_embeddings(self):
        return self.embeddings.shape_embed

    def set_shape_embeddings(self, value):
        self.embeddings.shape_embed = value

    # Copied from transformers.models.bert.modeling_bert.BertModel._prune_heads
    def _prune_heads(self, heads_to_prune):
        """
        Prunes heads of the model. heads_to_prune: dict of {layer_num: list of heads to prune in this layer} See base
        class PreTrainedModel
        """
        for layer, heads in heads_to_prune.items():
            self.encoder.layer[layer].attention.prune_heads(heads)

    def forward(
        self,
        input_ids: Optional[mindspore.Tensor] = None,
        input_shape_ids: Optional[mindspore.Tensor] = None,
        input_pronunciation_ids: Optional[mindspore.Tensor] = None,
        attention_mask: Optional[mindspore.Tensor] = None,
        token_type_ids: Optional[mindspore.Tensor] = None,
        position_ids: Optional[mindspore.Tensor] = None,
        head_mask: Optional[mindspore.Tensor] = None,
        inputs_embeds: Optional[mindspore.Tensor] = None,
        encoder_hidden_states: Optional[mindspore.Tensor] = None,
        encoder_attention_mask: Optional[mindspore.Tensor] = None,
        past_key_values: Optional[List[mindspore.Tensor]] = None,
        use_cache: Optional[bool] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
    ) -> Union[Tuple[mindspore.Tensor], BaseModelOutputWithPoolingAndCrossAttentions]:
        r"""
        Args:
            encoder_hidden_states  (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
                Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if
                the model is configured as a decoder.
            encoder_attention_mask (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*):
                Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in
                the cross-attention if the model is configured as a decoder. Mask values selected in `[0, 1]`:

                - 1 for tokens that are **not masked**,
                - 0 for tokens that are **masked**.
            past_key_values (`tuple(tuple(torch.FloatTensor))` of length `config.n_layers` with each tuple having 4 tensors
                of shape `(batch_size, num_heads, sequence_length - 1, embed_size_per_head)`):
                Contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding.
                If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those that
                don't have their past key value states given to this model) of shape `(batch_size, 1)` instead of all
                `decoder_input_ids` of shape `(batch_size, sequence_length)`.
            use_cache (`bool`, *optional*):
                If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see
                `past_key_values`).
        """
        output_attentions = (
            output_attentions
            if output_attentions is not None
            else self.config.output_attentions
        )
        output_hidden_states = (
            output_hidden_states
            if output_hidden_states is not None
            else self.config.output_hidden_states
        )
        return_dict = (
            return_dict if return_dict is not None else self.config.use_return_dict
        )

        if self.config.is_decoder:
            use_cache = use_cache if use_cache is not None else self.config.use_cache
        else:
            use_cache = False

        if input_ids is not None and inputs_embeds is not None:
            raise ValueError(
                "You cannot specify both input_ids and inputs_embeds at the same time"
            )
        elif input_ids is not None:
            self.warn_if_padding_and_no_attention_mask(input_ids, attention_mask)
            input_shape = input_ids.shape
        elif inputs_embeds is not None:
            input_shape = inputs_embeds.shape[:-1]
        else:
            raise ValueError("You have to specify either input_ids or inputs_embeds")

        batch_size, seq_length = input_shape

        # past_key_values_length
        past_key_values_length = (
            past_key_values[0][0].shape[2] if past_key_values is not None else 0
        )

        if attention_mask is None:
            attention_mask = ops.ones((batch_size, seq_length + past_key_values_length))

        if token_type_ids is None:
            if hasattr(self.embeddings, "token_type_ids"):
                buffered_token_type_ids = self.embeddings.token_type_ids[:, :seq_length]
                buffered_token_type_ids_expanded = buffered_token_type_ids.broadcast_to(
                    (batch_size, seq_length)
                )
                token_type_ids = buffered_token_type_ids_expanded
            else:
                token_type_ids = ops.zeros(input_shape, dtype=mindspore.int64)

        # We can provide a self-attention mask of dimensions [batch_size, from_seq_length, to_seq_length]
        # ourselves in which case we just need to make it broadcastable to all heads.
        extended_attention_mask: mindspore.Tensor = self.get_extended_attention_mask(
            attention_mask, input_shape
        )

        # If a 2D or 3D attention mask is provided for the cross-attention
        # we need to make broadcastable to [batch_size, num_heads, seq_length, seq_length]
        if self.config.is_decoder and encoder_hidden_states is not None:
            encoder_batch_size, encoder_sequence_length, _ = encoder_hidden_states.shape
            encoder_hidden_shape = (encoder_batch_size, encoder_sequence_length)
            if encoder_attention_mask is None:
                encoder_attention_mask = ops.ones(encoder_hidden_shape)
            encoder_extended_attention_mask = self.invert_attention_mask(
                encoder_attention_mask
            )
        else:
            encoder_extended_attention_mask = None

        # Prepare head mask if needed
        # 1.0 in head_mask indicate we keep the head
        # attention_probs has shape bsz x n_heads x N x N
        # input head_mask has shape [num_heads] or [num_hidden_layers x num_heads]
        # and head_mask is converted to shape [num_hidden_layers x batch x num_heads x seq_length x seq_length]
        head_mask = self.get_head_mask(head_mask, self.config.num_hidden_layers)

        embedding_output = self.embeddings(
            input_ids=input_ids,
            input_shape_ids=input_shape_ids,
            input_pronunciation_ids=input_pronunciation_ids,
            position_ids=position_ids,
            token_type_ids=token_type_ids,
            inputs_embeds=inputs_embeds,
            past_key_values_length=past_key_values_length,
        )
        encoder_outputs = self.encoder(
            embedding_output,
            attention_mask=extended_attention_mask,
            head_mask=head_mask,
            encoder_hidden_states=encoder_hidden_states,
            encoder_attention_mask=encoder_extended_attention_mask,
            past_key_values=past_key_values,
            use_cache=use_cache,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )
        sequence_output = encoder_outputs[0]
        pooled_output = (
            self.pooler(sequence_output) if self.pooler is not None else None
        )

        if not return_dict:
            return (sequence_output, pooled_output) + encoder_outputs[1:]

        return BaseModelOutputWithPoolingAndCrossAttentions(
            last_hidden_state=sequence_output,
            pooler_output=pooled_output,
            past_key_values=encoder_outputs.past_key_values,
            hidden_states=encoder_outputs.hidden_states,
            attentions=encoder_outputs.attentions,
            cross_attentions=encoder_outputs.cross_attentions,
        )

mindnlp.transformers.models.roc_bert.modeling_roc_bert.RoCBertModel.forward(input_ids=None, input_shape_ids=None, input_pronunciation_ids=None, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, encoder_hidden_states=None, encoder_attention_mask=None, past_key_values=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None)

PARAMETER DESCRIPTION
encoder_hidden_states

Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if the model is configured as a decoder.

TYPE: (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional* DEFAULT: None

encoder_attention_mask

Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in the cross-attention if the model is configured as a decoder. Mask values selected in [0, 1]:

  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.

TYPE: `torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional* DEFAULT: None

use_cache

If set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values).

TYPE: `bool`, *optional* DEFAULT: None

Source code in mindnlp/transformers/models/roc_bert/modeling_roc_bert.py 
 874
 875
 876
 877
 878
 879
 880
 881
 882
 883
 884
 885
 886
 887
 888
 889
 890
 891
 892
 893
 894
 895
 896
 897
 898
 899
 900
 901
 902
 903
 904
 905
 906
 907
 908
 909
 910
 911
 912
 913
 914
 915
 916
 917
 918
 919
 920
 921
 922
 923
 924
 925
 926
 927
 928
 929
 930
 931
 932
 933
 934
 935
 936
 937
 938
 939
 940
 941
 942
 943
 944
 945
 946
 947
 948
 949
 950
 951
 952
 953
 954
 955
 956
 957
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
def forward(
    self,
    input_ids: Optional[mindspore.Tensor] = None,
    input_shape_ids: Optional[mindspore.Tensor] = None,
    input_pronunciation_ids: Optional[mindspore.Tensor] = None,
    attention_mask: Optional[mindspore.Tensor] = None,
    token_type_ids: Optional[mindspore.Tensor] = None,
    position_ids: Optional[mindspore.Tensor] = None,
    head_mask: Optional[mindspore.Tensor] = None,
    inputs_embeds: Optional[mindspore.Tensor] = None,
    encoder_hidden_states: Optional[mindspore.Tensor] = None,
    encoder_attention_mask: Optional[mindspore.Tensor] = None,
    past_key_values: Optional[List[mindspore.Tensor]] = None,
    use_cache: Optional[bool] = None,
    output_attentions: Optional[bool] = None,
    output_hidden_states: Optional[bool] = None,
    return_dict: Optional[bool] = None,
) -> Union[Tuple[mindspore.Tensor], BaseModelOutputWithPoolingAndCrossAttentions]:
    r"""
    Args:
        encoder_hidden_states  (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
            Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if
            the model is configured as a decoder.
        encoder_attention_mask (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*):
            Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in
            the cross-attention if the model is configured as a decoder. Mask values selected in `[0, 1]`:

            - 1 for tokens that are **not masked**,
            - 0 for tokens that are **masked**.
        past_key_values (`tuple(tuple(torch.FloatTensor))` of length `config.n_layers` with each tuple having 4 tensors
            of shape `(batch_size, num_heads, sequence_length - 1, embed_size_per_head)`):
            Contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding.
            If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those that
            don't have their past key value states given to this model) of shape `(batch_size, 1)` instead of all
            `decoder_input_ids` of shape `(batch_size, sequence_length)`.
        use_cache (`bool`, *optional*):
            If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see
            `past_key_values`).
    """
    output_attentions = (
        output_attentions
        if output_attentions is not None
        else self.config.output_attentions
    )
    output_hidden_states = (
        output_hidden_states
        if output_hidden_states is not None
        else self.config.output_hidden_states
    )
    return_dict = (
        return_dict if return_dict is not None else self.config.use_return_dict
    )

    if self.config.is_decoder:
        use_cache = use_cache if use_cache is not None else self.config.use_cache
    else:
        use_cache = False

    if input_ids is not None and inputs_embeds is not None:
        raise ValueError(
            "You cannot specify both input_ids and inputs_embeds at the same time"
        )
    elif input_ids is not None:
        self.warn_if_padding_and_no_attention_mask(input_ids, attention_mask)
        input_shape = input_ids.shape
    elif inputs_embeds is not None:
        input_shape = inputs_embeds.shape[:-1]
    else:
        raise ValueError("You have to specify either input_ids or inputs_embeds")

    batch_size, seq_length = input_shape

    # past_key_values_length
    past_key_values_length = (
        past_key_values[0][0].shape[2] if past_key_values is not None else 0
    )

    if attention_mask is None:
        attention_mask = ops.ones((batch_size, seq_length + past_key_values_length))

    if token_type_ids is None:
        if hasattr(self.embeddings, "token_type_ids"):
            buffered_token_type_ids = self.embeddings.token_type_ids[:, :seq_length]
            buffered_token_type_ids_expanded = buffered_token_type_ids.broadcast_to(
                (batch_size, seq_length)
            )
            token_type_ids = buffered_token_type_ids_expanded
        else:
            token_type_ids = ops.zeros(input_shape, dtype=mindspore.int64)

    # We can provide a self-attention mask of dimensions [batch_size, from_seq_length, to_seq_length]
    # ourselves in which case we just need to make it broadcastable to all heads.
    extended_attention_mask: mindspore.Tensor = self.get_extended_attention_mask(
        attention_mask, input_shape
    )

    # If a 2D or 3D attention mask is provided for the cross-attention
    # we need to make broadcastable to [batch_size, num_heads, seq_length, seq_length]
    if self.config.is_decoder and encoder_hidden_states is not None:
        encoder_batch_size, encoder_sequence_length, _ = encoder_hidden_states.shape
        encoder_hidden_shape = (encoder_batch_size, encoder_sequence_length)
        if encoder_attention_mask is None:
            encoder_attention_mask = ops.ones(encoder_hidden_shape)
        encoder_extended_attention_mask = self.invert_attention_mask(
            encoder_attention_mask
        )
    else:
        encoder_extended_attention_mask = None

    # Prepare head mask if needed
    # 1.0 in head_mask indicate we keep the head
    # attention_probs has shape bsz x n_heads x N x N
    # input head_mask has shape [num_heads] or [num_hidden_layers x num_heads]
    # and head_mask is converted to shape [num_hidden_layers x batch x num_heads x seq_length x seq_length]
    head_mask = self.get_head_mask(head_mask, self.config.num_hidden_layers)

    embedding_output = self.embeddings(
        input_ids=input_ids,
        input_shape_ids=input_shape_ids,
        input_pronunciation_ids=input_pronunciation_ids,
        position_ids=position_ids,
        token_type_ids=token_type_ids,
        inputs_embeds=inputs_embeds,
        past_key_values_length=past_key_values_length,
    )
    encoder_outputs = self.encoder(
        embedding_output,
        attention_mask=extended_attention_mask,
        head_mask=head_mask,
        encoder_hidden_states=encoder_hidden_states,
        encoder_attention_mask=encoder_extended_attention_mask,
        past_key_values=past_key_values,
        use_cache=use_cache,
        output_attentions=output_attentions,
        output_hidden_states=output_hidden_states,
        return_dict=return_dict,
    )
    sequence_output = encoder_outputs[0]
    pooled_output = (
        self.pooler(sequence_output) if self.pooler is not None else None
    )

    if not return_dict:
        return (sequence_output, pooled_output) + encoder_outputs[1:]

    return BaseModelOutputWithPoolingAndCrossAttentions(
        last_hidden_state=sequence_output,
        pooler_output=pooled_output,
        past_key_values=encoder_outputs.past_key_values,
        hidden_states=encoder_outputs.hidden_states,
        attentions=encoder_outputs.attentions,
        cross_attentions=encoder_outputs.cross_attentions,
    )

mindnlp.transformers.models.roc_bert.modeling_roc_bert.RoCBertPreTrainedModel

Bases: PreTrainedModel

An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained models.

Source code in mindnlp/transformers/models/roc_bert/modeling_roc_bert.py 
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
class RoCBertPreTrainedModel(PreTrainedModel):
    """
    An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained
    models.
    """

    config_class = RoCBertConfig
    base_model_prefix = "roc_bert"
    supports_gradient_checkpointing = True

    def _init_weights(self, cell):
        """Initialize the weights"""
        if isinstance(cell, nn.Linear):
            # Slightly different from the TF version which uses truncated_normal for initialization
            # cf https://github.com/pytorch/pytorch/pull/5617
            cell.weight.set_data(
                initializer(
                    Normal(self.config.initializer_range),
                    cell.weight.shape,
                    cell.weight.dtype,
                )
            )
            if cell.bias:
                cell.bias.set_data(
                    initializer("zeros", cell.bias.shape, cell.bias.dtype)
                )
        elif isinstance(cell, nn.Embedding):
            weight = np.random.normal(
                0.0, self.config.initializer_range, cell.weight.shape
            )
            if cell.padding_idx:
                weight[cell.padding_idx] = 0

            cell.weight.set_data(mindspore.Tensor(weight, cell.weight.dtype))
        elif isinstance(cell, nn.LayerNorm):
            cell.bias.set_data(initializer("zeros", cell.bias.shape, cell.bias.dtype))
            cell.weight.set_data(
                initializer("ones", cell.weight.shape, cell.weight.dtype)
            )

mindnlp.transformers.models.roc_bert.tokenization_roc_bert

Tokenization classes for RoCBert.

mindnlp.transformers.models.roc_bert.tokenization_roc_bert.RoCBertBasicTokenizer

Constructs a RoCBertBasicTokenizer that will run basic tokenization (punctuation splitting, lower casing, etc.).

PARAMETER DESCRIPTION
do_lower_case

Whether or not to lowercase the input when tokenizing.

TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True

never_split

Collection of tokens which will never be split during tokenization. Only has an effect when do_basic_tokenize=True

TYPE: `Iterable`, *optional* DEFAULT: None

tokenize_chinese_chars

Whether or not to tokenize Chinese characters.

This should likely be deactivated for Japanese (see this issue).

TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True

strip_accents

Whether or not to strip all accents. If this option is not specified, then it will be determined by the value for lowercase (as in the original BERT).

TYPE: `bool`, *optional* DEFAULT: None

do_split_on_punc

In some instances we want to skip the basic punctuation splitting so that later tokenization can capture the full context of the words, such as contractions.

TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True

Source code in mindnlp/transformers/models/roc_bert/tokenization_roc_bert.py 
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
class RoCBertBasicTokenizer:
    """
    Constructs a RoCBertBasicTokenizer that will run basic tokenization (punctuation splitting, lower casing, etc.).

    Args:
        do_lower_case (`bool`, *optional*, defaults to `True`):
            Whether or not to lowercase the input when tokenizing.
        never_split (`Iterable`, *optional*):
            Collection of tokens which will never be split during tokenization. Only has an effect when
            `do_basic_tokenize=True`
        tokenize_chinese_chars (`bool`, *optional*, defaults to `True`):
            Whether or not to tokenize Chinese characters.

            This should likely be deactivated for Japanese (see this
            [issue](https://github.com/huggingface/transformers/issues/328)).
        strip_accents (`bool`, *optional*):
            Whether or not to strip all accents. If this option is not specified, then it will be determined by the
            value for `lowercase` (as in the original BERT).
        do_split_on_punc (`bool`, *optional*, defaults to `True`):
            In some instances we want to skip the basic punctuation splitting so that later tokenization can capture
            the full context of the words, such as contractions.
    """

    def __init__(
        self,
        do_lower_case=True,
        never_split=None,
        tokenize_chinese_chars=True,
        strip_accents=None,
        do_split_on_punc=True,
    ):
        if never_split is None:
            never_split = []
        self.do_lower_case = do_lower_case
        self.never_split = set(never_split)
        self.tokenize_chinese_chars = tokenize_chinese_chars
        self.strip_accents = strip_accents
        self.do_split_on_punc = do_split_on_punc

    def tokenize(self, text, never_split=None):
        """
        Basic Tokenization of a piece of text. For sub-word tokenization, see WordPieceTokenizer.

        Args:
            never_split (`List[str]`, *optional*)
                Kept for backward compatibility purposes. Now implemented directly at the base class level (see
                [`PreTrainedTokenizer.tokenize`]) List of token not to split.
        """
        # union() returns a new set by concatenating the two sets.
        never_split = (
            self.never_split.union(set(never_split))
            if never_split
            else self.never_split
        )
        text = self._clean_text(text)

        # This was added on November 1st, 2018 for the multilingual and Chinese
        # models. This is also applied to the English models now, but it doesn't
        # matter since the English models were not trained on any Chinese data
        # and generally don't have any Chinese data in them (there are Chinese
        # characters in the vocabulary because Wikipedia does have some Chinese
        # words in the English Wikipedia.).
        if self.tokenize_chinese_chars:
            text = self._tokenize_chinese_chars(text)
        # prevents treating the same character with different unicode codepoints as different characters
        unicode_normalized_text = unicodedata.normalize("NFC", text)
        orig_tokens = whitespace_tokenize(unicode_normalized_text)
        split_tokens = []
        for token in orig_tokens:
            if token not in never_split:
                if self.do_lower_case:
                    token = token.lower()
                    if self.strip_accents is not False:
                        token = self._run_strip_accents(token)
                elif self.strip_accents:
                    token = self._run_strip_accents(token)
            split_tokens.extend(self._run_split_on_punc(token, never_split))

        output_tokens = whitespace_tokenize(" ".join(split_tokens))
        return output_tokens

    def _run_strip_accents(self, text):
        """Strips accents from a piece of text."""
        text = unicodedata.normalize("NFD", text)
        output = []
        for char in text:
            cat = unicodedata.category(char)
            if cat == "Mn":
                continue
            output.append(char)
        return "".join(output)

    def _run_split_on_punc(self, text, never_split=None):
        """Splits punctuation on a piece of text."""
        if not self.do_split_on_punc or (
            never_split is not None and text in never_split
        ):
            return [text]
        chars = list(text)
        i = 0
        start_new_word = True
        output = []
        while i < len(chars):
            char = chars[i]
            if _is_punctuation(char):
                output.append([char])
                start_new_word = True
            else:
                if start_new_word:
                    output.append([])
                start_new_word = False
                output[-1].append(char)
            i += 1

        return ["".join(x) for x in output]

    def _tokenize_chinese_chars(self, text):
        """Adds whitespace around any CJK character."""
        output = []
        for char in text:
            cp = ord(char)
            if self._is_chinese_char(cp):
                output.append(" ")
                output.append(char)
                output.append(" ")
            else:
                output.append(char)
        return "".join(output)

    def _is_chinese_char(self, cp):
        """Checks whether CP is the codepoint of a CJK character."""
        # This defines a "chinese character" as anything in the CJK Unicode block:
        #   https://en.wikipedia.org/wiki/CJK_Unified_Ideographs_(Unicode_block)
        #
        # Note that the CJK Unicode block is NOT all Japanese and Korean characters,
        # despite its name. The modern Korean Hangul alphabet is a different block,
        # as is Japanese Hiragana and Katakana. Those alphabets are used to write
        # space-separated words, so they are not treated specially and handled
        # like the all of the other languages.
        if (
            (cp >= 0x4E00 and cp <= 0x9FFF)
            or (cp >= 0x3400 and cp <= 0x4DBF)  #
            or (cp >= 0x20000 and cp <= 0x2A6DF)  #
            or (cp >= 0x2A700 and cp <= 0x2B73F)  #
            or (cp >= 0x2B740 and cp <= 0x2B81F)  #
            or (cp >= 0x2B820 and cp <= 0x2CEAF)  #
            or (cp >= 0xF900 and cp <= 0xFAFF)
            or (cp >= 0x2F800 and cp <= 0x2FA1F)  #
        ):  #
            return True

        return False

    def _clean_text(self, text):
        """Performs invalid character removal and whitespace cleanup on text."""
        output = []
        for char in text:
            cp = ord(char)
            if cp == 0 or cp == 0xFFFD or _is_control(char):
                continue
            if _is_whitespace(char):
                output.append(" ")
            else:
                output.append(char)
        return "".join(output)

mindnlp.transformers.models.roc_bert.tokenization_roc_bert.RoCBertBasicTokenizer.tokenize(text, never_split=None)

Basic Tokenization of a piece of text. For sub-word tokenization, see WordPieceTokenizer.

Source code in mindnlp/transformers/models/roc_bert/tokenization_roc_bert.py 
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
def tokenize(self, text, never_split=None):
    """
    Basic Tokenization of a piece of text. For sub-word tokenization, see WordPieceTokenizer.

    Args:
        never_split (`List[str]`, *optional*)
            Kept for backward compatibility purposes. Now implemented directly at the base class level (see
            [`PreTrainedTokenizer.tokenize`]) List of token not to split.
    """
    # union() returns a new set by concatenating the two sets.
    never_split = (
        self.never_split.union(set(never_split))
        if never_split
        else self.never_split
    )
    text = self._clean_text(text)

    # This was added on November 1st, 2018 for the multilingual and Chinese
    # models. This is also applied to the English models now, but it doesn't
    # matter since the English models were not trained on any Chinese data
    # and generally don't have any Chinese data in them (there are Chinese
    # characters in the vocabulary because Wikipedia does have some Chinese
    # words in the English Wikipedia.).
    if self.tokenize_chinese_chars:
        text = self._tokenize_chinese_chars(text)
    # prevents treating the same character with different unicode codepoints as different characters
    unicode_normalized_text = unicodedata.normalize("NFC", text)
    orig_tokens = whitespace_tokenize(unicode_normalized_text)
    split_tokens = []
    for token in orig_tokens:
        if token not in never_split:
            if self.do_lower_case:
                token = token.lower()
                if self.strip_accents is not False:
                    token = self._run_strip_accents(token)
            elif self.strip_accents:
                token = self._run_strip_accents(token)
        split_tokens.extend(self._run_split_on_punc(token, never_split))

    output_tokens = whitespace_tokenize(" ".join(split_tokens))
    return output_tokens

mindnlp.transformers.models.roc_bert.tokenization_roc_bert.RoCBertTokenizer

Bases: PreTrainedTokenizer

Construct a RoCBert tokenizer. Based on WordPiece. This tokenizer inherits from [PreTrainedTokenizer] which contains most of the main methods. Users should refer to this superclass for more information regarding those methods.

PARAMETER DESCRIPTION
vocab_file

File containing the vocabulary.

TYPE: `str`

word_shape_file

File containing the word => shape info.

TYPE: `str`

word_pronunciation_file

File containing the word => pronunciation info.

TYPE: `str`

do_lower_case

Whether or not to lowercase the input when tokenizing.

TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True

do_basic_tokenize

Whether or not to do basic tokenization before WordPiece.

TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True

never_split

Collection of tokens which will never be split during tokenization. Only has an effect when do_basic_tokenize=True

TYPE: `Iterable`, *optional* DEFAULT: None

unk_token

The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this token instead.

TYPE: `str`, *optional*, defaults to `"[UNK]"` DEFAULT: '[UNK]'

sep_token

The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for sequence classification or for a text and a question for question answering. It is also used as the last token of a sequence built with special tokens.

TYPE: `str`, *optional*, defaults to `"[SEP]"` DEFAULT: '[SEP]'

pad_token

The token used for padding, for example when batching sequences of different lengths.

TYPE: `str`, *optional*, defaults to `"[PAD]"` DEFAULT: '[PAD]'

cls_token

The classifier token which is used when doing sequence classification (classification of the whole sequence instead of per-token classification). It is the first token of the sequence when built with special tokens.

TYPE: `str`, *optional*, defaults to `"[CLS]"` DEFAULT: '[CLS]'

mask_token

The token used for masking values. This is the token used when training this model with masked language modeling. This is the token which the model will try to predict.

TYPE: `str`, *optional*, defaults to `"[MASK]"` DEFAULT: '[MASK]'

tokenize_chinese_chars

Whether or not to tokenize Chinese characters. This should likely be deactivated for Japanese (see this issue).

TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True

strip_accents

Whether or not to strip all accents. If this option is not specified, then it will be determined by the value for lowercase (as in the original BERT).

TYPE: `bool`, *optional* DEFAULT: None

Source code in mindnlp/transformers/models/roc_bert/tokenization_roc_bert.py 
  76
  77
  78
  79
  80
  81
  82
  83
  84
  85
  86
  87
  88
  89
  90
  91
  92
  93
  94
  95
  96
  97
  98
  99
 100
 101
 102
 103
 104
 105
 106
 107
 108
 109
 110
 111
 112
 113
 114
 115
 116
 117
 118
 119
 120
 121
 122
 123
 124
 125
 126
 127
 128
 129
 130
 131
 132
 133
 134
 135
 136
 137
 138
 139
 140
 141
 142
 143
 144
 145
 146
 147
 148
 149
 150
 151
 152
 153
 154
 155
 156
 157
 158
 159
 160
 161
 162
 163
 164
 165
 166
 167
 168
 169
 170
 171
 172
 173
 174
 175
 176
 177
 178
 179
 180
 181
 182
 183
 184
 185
 186
 187
 188
 189
 190
 191
 192
 193
 194
 195
 196
 197
 198
 199
 200
 201
 202
 203
 204
 205
 206
 207
 208
 209
 210
 211
 212
 213
 214
 215
 216
 217
 218
 219
 220
 221
 222
 223
 224
 225
 226
 227
 228
 229
 230
 231
 232
 233
 234
 235
 236
 237
 238
 239
 240
 241
 242
 243
 244
 245
 246
 247
 248
 249
 250
 251
 252
 253
 254
 255
 256
 257
 258
 259
 260
 261
 262
 263
 264
 265
 266
 267
 268
 269
 270
 271
 272
 273
 274
 275
 276
 277
 278
 279
 280
 281
 282
 283
 284
 285
 286
 287
 288
 289
 290
 291
 292
 293
 294
 295
 296
 297
 298
 299
 300
 301
 302
 303
 304
 305
 306
 307
 308
 309
 310
 311
 312
 313
 314
 315
 316
 317
 318
 319
 320
 321
 322
 323
 324
 325
 326
 327
 328
 329
 330
 331
 332
 333
 334
 335
 336
 337
 338
 339
 340
 341
 342
 343
 344
 345
 346
 347
 348
 349
 350
 351
 352
 353
 354
 355
 356
 357
 358
 359
 360
 361
 362
 363
 364
 365
 366
 367
 368
 369
 370
 371
 372
 373
 374
 375
 376
 377
 378
 379
 380
 381
 382
 383
 384
 385
 386
 387
 388
 389
 390
 391
 392
 393
 394
 395
 396
 397
 398
 399
 400
 401
 402
 403
 404
 405
 406
 407
 408
 409
 410
 411
 412
 413
 414
 415
 416
 417
 418
 419
 420
 421
 422
 423
 424
 425
 426
 427
 428
 429
 430
 431
 432
 433
 434
 435
 436
 437
 438
 439
 440
 441
 442
 443
 444
 445
 446
 447
 448
 449
 450
 451
 452
 453
 454
 455
 456
 457
 458
 459
 460
 461
 462
 463
 464
 465
 466
 467
 468
 469
 470
 471
 472
 473
 474
 475
 476
 477
 478
 479
 480
 481
 482
 483
 484
 485
 486
 487
 488
 489
 490
 491
 492
 493
 494
 495
 496
 497
 498
 499
 500
 501
 502
 503
 504
 505
 506
 507
 508
 509
 510
 511
 512
 513
 514
 515
 516
 517
 518
 519
 520
 521
 522
 523
 524
 525
 526
 527
 528
 529
 530
 531
 532
 533
 534
 535
 536
 537
 538
 539
 540
 541
 542
 543
 544
 545
 546
 547
 548
 549
 550
 551
 552
 553
 554
 555
 556
 557
 558
 559
 560
 561
 562
 563
 564
 565
 566
 567
 568
 569
 570
 571
 572
 573
 574
 575
 576
 577
 578
 579
 580
 581
 582
 583
 584
 585
 586
 587
 588
 589
 590
 591
 592
 593
 594
 595
 596
 597
 598
 599
 600
 601
 602
 603
 604
 605
 606
 607
 608
 609
 610
 611
 612
 613
 614
 615
 616
 617
 618
 619
 620
 621
 622
 623
 624
 625
 626
 627
 628
 629
 630
 631
 632
 633
 634
 635
 636
 637
 638
 639
 640
 641
 642
 643
 644
 645
 646
 647
 648
 649
 650
 651
 652
 653
 654
 655
 656
 657
 658
 659
 660
 661
 662
 663
 664
 665
 666
 667
 668
 669
 670
 671
 672
 673
 674
 675
 676
 677
 678
 679
 680
 681
 682
 683
 684
 685
 686
 687
 688
 689
 690
 691
 692
 693
 694
 695
 696
 697
 698
 699
 700
 701
 702
 703
 704
 705
 706
 707
 708
 709
 710
 711
 712
 713
 714
 715
 716
 717
 718
 719
 720
 721
 722
 723
 724
 725
 726
 727
 728
 729
 730
 731
 732
 733
 734
 735
 736
 737
 738
 739
 740
 741
 742
 743
 744
 745
 746
 747
 748
 749
 750
 751
 752
 753
 754
 755
 756
 757
 758
 759
 760
 761
 762
 763
 764
 765
 766
 767
 768
 769
 770
 771
 772
 773
 774
 775
 776
 777
 778
 779
 780
 781
 782
 783
 784
 785
 786
 787
 788
 789
 790
 791
 792
 793
 794
 795
 796
 797
 798
 799
 800
 801
 802
 803
 804
 805
 806
 807
 808
 809
 810
 811
 812
 813
 814
 815
 816
 817
 818
 819
 820
 821
 822
 823
 824
 825
 826
 827
 828
 829
 830
 831
 832
 833
 834
 835
 836
 837
 838
 839
 840
 841
 842
 843
 844
 845
 846
 847
 848
 849
 850
 851
 852
 853
 854
 855
 856
 857
 858
 859
 860
 861
 862
 863
 864
 865
 866
 867
 868
 869
 870
 871
 872
 873
 874
 875
 876
 877
 878
 879
 880
 881
 882
 883
 884
 885
 886
 887
 888
 889
 890
 891
 892
 893
 894
 895
 896
 897
 898
 899
 900
 901
 902
 903
 904
 905
 906
 907
 908
 909
 910
 911
 912
 913
 914
 915
 916
 917
 918
 919
 920
 921
 922
 923
 924
 925
 926
 927
 928
 929
 930
 931
 932
 933
 934
 935
 936
 937
 938
 939
 940
 941
 942
 943
 944
 945
 946
 947
 948
 949
 950
 951
 952
 953
 954
 955
 956
 957
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
class RoCBertTokenizer(PreTrainedTokenizer):
    r"""
    Construct a RoCBert tokenizer. Based on WordPiece. This tokenizer inherits from [`PreTrainedTokenizer`] which
    contains most of the main methods. Users should refer to this superclass for more information regarding those
    methods.

    Args:
        vocab_file (`str`):
            File containing the vocabulary.
        word_shape_file (`str`):
            File containing the word => shape info.
        word_pronunciation_file (`str`):
            File containing the word => pronunciation info.
        do_lower_case (`bool`, *optional*, defaults to `True`):
            Whether or not to lowercase the input when tokenizing.
        do_basic_tokenize (`bool`, *optional*, defaults to `True`):
            Whether or not to do basic tokenization before WordPiece.
        never_split (`Iterable`, *optional*):
            Collection of tokens which will never be split during tokenization. Only has an effect when
            `do_basic_tokenize=True`
        unk_token (`str`, *optional*, defaults to `"[UNK]"`):
            The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
            token instead.
        sep_token (`str`, *optional*, defaults to `"[SEP]"`):
            The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for
            sequence classification or for a text and a question for question answering. It is also used as the last
            token of a sequence built with special tokens.
        pad_token (`str`, *optional*, defaults to `"[PAD]"`):
            The token used for padding, for example when batching sequences of different lengths.
        cls_token (`str`, *optional*, defaults to `"[CLS]"`):
            The classifier token which is used when doing sequence classification (classification of the whole sequence
            instead of per-token classification). It is the first token of the sequence when built with special tokens.
        mask_token (`str`, *optional*, defaults to `"[MASK]"`):
            The token used for masking values. This is the token used when training this model with masked language
            modeling. This is the token which the model will try to predict.
        tokenize_chinese_chars (`bool`, *optional*, defaults to `True`):
            Whether or not to tokenize Chinese characters. This should likely be deactivated for Japanese (see this
            [issue](https://github.com/huggingface/transformers/issues/328)).
        strip_accents (`bool`, *optional*):
            Whether or not to strip all accents. If this option is not specified, then it will be determined by the
            value for `lowercase` (as in the original BERT).
    """

    vocab_files_names = VOCAB_FILES_NAMES

    def __init__(
        self,
        vocab_file,
        word_shape_file,
        word_pronunciation_file,
        do_lower_case=True,
        do_basic_tokenize=True,
        never_split=None,
        unk_token="[UNK]",
        sep_token="[SEP]",
        pad_token="[PAD]",
        cls_token="[CLS]",
        mask_token="[MASK]",
        tokenize_chinese_chars=True,
        strip_accents=None,
        **kwargs,
    ):
        for cur_file in [vocab_file, word_shape_file, word_pronunciation_file]:
            if cur_file is None or not os.path.isfile(cur_file):
                raise ValueError(
                    f"Can't find a vocabulary file at path '{vocab_file}'. To load the vocabulary from a Google "
                    "pretrained model use `tokenizer = RoCBertTokenizer.from_pretrained(PRETRAINED_MODEL_NAME)`"
                )

        self.vocab = load_vocab(vocab_file)

        with open(word_shape_file, "r", encoding="utf8") as in_file:
            self.word_shape = json.load(in_file)

        with open(word_pronunciation_file, "r", encoding="utf8") as in_file:
            self.word_pronunciation = json.load(in_file)

        self.ids_to_tokens = collections.OrderedDict(
            [(ids, tok) for tok, ids in self.vocab.items()]
        )

        self.do_basic_tokenize = do_basic_tokenize
        if do_basic_tokenize:
            self.basic_tokenizer = RoCBertBasicTokenizer(
                do_lower_case=do_lower_case,
                never_split=never_split,
                tokenize_chinese_chars=tokenize_chinese_chars,
                strip_accents=strip_accents,
            )
        self.wordpiece_tokenizer = RoCBertWordpieceTokenizer(
            vocab=self.vocab, unk_token=str(unk_token)
        )
        super().__init__(
            do_lower_case=do_lower_case,
            do_basic_tokenize=do_basic_tokenize,
            never_split=never_split,
            unk_token=unk_token,
            sep_token=sep_token,
            pad_token=pad_token,
            cls_token=cls_token,
            mask_token=mask_token,
            tokenize_chinese_chars=tokenize_chinese_chars,
            strip_accents=strip_accents,
            **kwargs,
        )

    @property
    def do_lower_case(self):
        return self.basic_tokenizer.do_lower_case

    @property
    def vocab_size(self):
        return len(self.vocab)

    # Copied from transformers.models.bert.tokenization_bert.BertTokenizer.get_vocab
    def get_vocab(self):
        return dict(self.vocab, **self.added_tokens_encoder)

    # Copied from transformers.models.bert.tokenization_bert.BertTokenizer._tokenize
    def _tokenize(self, text, split_special_tokens=False):
        split_tokens = []
        if self.do_basic_tokenize:
            for token in self.basic_tokenizer.tokenize(
                text,
                never_split=(
                    self.all_special_tokens if not split_special_tokens else None
                ),
            ):
                # If the token is part of the never_split set
                if token in self.basic_tokenizer.never_split:
                    split_tokens.append(token)
                else:
                    split_tokens += self.wordpiece_tokenizer.tokenize(token)
        else:
            split_tokens = self.wordpiece_tokenizer.tokenize(text)
        return split_tokens

    def _encode_plus(
        self,
        text: Union[TextInput, PreTokenizedInput, EncodedInput],
        text_pair: Optional[Union[TextInput, PreTokenizedInput, EncodedInput]] = None,
        add_special_tokens: bool = True,
        padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
        truncation_strategy: TruncationStrategy = TruncationStrategy.DO_NOT_TRUNCATE,
        max_length: Optional[int] = None,
        stride: int = 0,
        is_split_into_words: bool = False,
        pad_to_multiple_of: Optional[int] = None,
        return_tensors: Optional[Union[str, TensorType]] = None,
        return_token_type_ids: Optional[bool] = None,
        return_attention_mask: Optional[bool] = None,
        return_overflowing_tokens: bool = False,
        return_special_tokens_mask: bool = False,
        return_offsets_mapping: bool = False,
        return_length: bool = False,
        verbose: bool = True,
        **kwargs,
    ) -> BatchEncoding:
        def get_input_ids(text):
            if isinstance(text, str):
                tokens = self.tokenize(text, **kwargs)
                tokens_ids = self.convert_tokens_to_ids(tokens)
                tokens_shape_ids = self.convert_tokens_to_shape_ids(tokens)
                tokens_proun_ids = self.convert_tokens_to_pronunciation_ids(tokens)
                return tokens_ids, tokens_shape_ids, tokens_proun_ids
            elif (
                isinstance(text, (list, tuple))
                and len(text) > 0
                and isinstance(text[0], str)
            ):
                if is_split_into_words:
                    tokens = list(
                        itertools.chain(
                            *(
                                self.tokenize(t, is_split_into_words=True, **kwargs)
                                for t in text
                            )
                        )
                    )
                    tokens_ids = self.convert_tokens_to_ids(tokens)
                    tokens_shape_ids = self.convert_tokens_to_shape_ids(tokens)
                    tokens_proun_ids = self.convert_tokens_to_pronunciation_ids(tokens)
                    return tokens_ids, tokens_shape_ids, tokens_proun_ids
                else:
                    tokens_ids = self.convert_tokens_to_ids(text)
                    tokens_shape_ids = self.convert_tokens_to_shape_ids(text)
                    tokens_proun_ids = self.convert_tokens_to_pronunciation_ids(text)
                    return tokens_ids, tokens_shape_ids, tokens_proun_ids
            elif (
                isinstance(text, (list, tuple))
                and len(text) > 0
                and isinstance(text[0], int)
            ):
                return (
                    text,
                    [0] * len(text),
                    [0] * len(text),
                )  # shape and proun id is pad_value
            else:
                if is_split_into_words:
                    raise ValueError(
                        f"Input {text} is not valid. Should be a string or a list/tuple of strings when"
                        " `is_split_into_words=True`."
                    )
                else:
                    raise ValueError(
                        f"Input {text} is not valid. Should be a string, a list/tuple of strings or a list/tuple of"
                        " integers."
                    )

        if return_offsets_mapping:
            raise NotImplementedError(
                "return_offset_mapping is not available when using Python tokenizers. "
                "To use this feature, change your tokenizer to one deriving from "
                "transformers.PreTrainedTokenizerFast. "
                "More information on available tokenizers at "
                "https://github.com/huggingface/transformers/pull/2674"
            )

        first_ids, first_shape_ids, first_proun_ids = get_input_ids(text)
        if text_pair is not None:
            second_ids, second_shape_ids, second_proun_ids = get_input_ids(text_pair)
        else:
            second_ids, second_shape_ids, second_proun_ids = None, None, None

        return self.prepare_for_model(
            first_ids,
            first_shape_ids,
            first_proun_ids,
            pair_ids=second_ids,
            pair_shape_ids=second_shape_ids,
            pair_pronunciation_ids=second_proun_ids,
            add_special_tokens=add_special_tokens,
            padding=padding_strategy.value,
            truncation=truncation_strategy.value,
            max_length=max_length,
            stride=stride,
            pad_to_multiple_of=pad_to_multiple_of,
            return_tensors=return_tensors,
            prepend_batch_axis=True,
            return_attention_mask=return_attention_mask,
            return_token_type_ids=return_token_type_ids,
            return_overflowing_tokens=return_overflowing_tokens,
            return_special_tokens_mask=return_special_tokens_mask,
            return_length=return_length,
            verbose=verbose,
        )

    def prepare_for_model(
        self,
        ids: List[int],
        shape_ids: List[int],
        pronunciation_ids: List[int],
        pair_ids: Optional[List[int]] = None,
        pair_shape_ids: Optional[List[int]] = None,
        pair_pronunciation_ids: Optional[List[int]] = None,
        add_special_tokens: bool = True,
        padding: Union[bool, str, PaddingStrategy] = False,
        truncation: Union[bool, str, TruncationStrategy] = None,
        max_length: Optional[int] = None,
        stride: int = 0,
        pad_to_multiple_of: Optional[int] = None,
        return_tensors: Optional[Union[str, TensorType]] = None,
        return_token_type_ids: Optional[bool] = None,
        return_attention_mask: Optional[bool] = None,
        return_overflowing_tokens: bool = False,
        return_special_tokens_mask: bool = False,
        return_offsets_mapping: bool = False,
        return_length: bool = False,
        verbose: bool = True,
        prepend_batch_axis: bool = False,
        **kwargs,
    ) -> BatchEncoding:
        """
        Prepares a sequence of input id, or a pair of sequences of inputs ids so that it can be used by the model. It
        adds special tokens, truncates sequences if overflowing while taking into account the special tokens and
        manages a moving window (with user defined stride) for overflowing tokens. Please Note, for *pair_ids*
        different than `None` and *truncation_strategy = longest_first* or `True`, it is not possible to return
        overflowing tokens. Such a combination of arguments will raise an error.

        Args:
            ids (`List[int]`):
                Tokenized input ids of the first sequence. Can be obtained from a string by chaining the `tokenize` and
                `convert_tokens_to_id` methods.
            shape_ids (`List[int]`):
                Tokenized input ids of the first sequence. Can be obtained from a string by chaining the `tokenize` and
                `convert_token_to_shape_id` methods.
            pronunciation_ids (`List[int]`):
                Tokenized input ids of the first sequence. Can be obtained from a string by chaining the `tokenize` and
                `convert_token_to_pronunciation_id` methods.
            pair_ids (`List[int]`, *optional*):
                Tokenized input ids of the second sequence. Can be obtained from a string by chaining the `tokenize`
                and `convert_tokens_to_id` methods.
            pair_shape_ids (`List[int]`, *optional*):
                Tokenized input ids of the second sequence. Can be obtained from a string by chaining the `tokenize`
                and `convert_token_to_shape_id` methods.
            pair_pronunciation_ids (`List[int]`, *optional*):
                Tokenized input ids of the second sequence. Can be obtained from a string by chaining the `tokenize`
                and `convert_token_to_pronunciation_id` methods.
        """

        # Backward compatibility for 'truncation_strategy', 'pad_to_max_length'
        padding_strategy, truncation_strategy, max_length, kwargs = (
            self._get_padding_truncation_strategies(
                padding=padding,
                truncation=truncation,
                max_length=max_length,
                pad_to_multiple_of=pad_to_multiple_of,
                verbose=verbose,
                **kwargs,
            )
        )

        pair = bool(pair_ids is not None)
        len_ids = len(ids)
        len_pair_ids = len(pair_ids) if pair else 0

        if return_token_type_ids and not add_special_tokens:
            raise ValueError(
                "Asking to return token_type_ids while setting add_special_tokens to False "
                "results in an undefined behavior. Please set add_special_tokens to True or "
                "set return_token_type_ids to None."
            )

        if (
            return_overflowing_tokens
            and truncation_strategy == TruncationStrategy.LONGEST_FIRST
            and pair_ids is not None
        ):
            raise ValueError(
                "Not possible to return overflowing tokens for pair of sequences with the "
                "`longest_first`. Please select another truncation strategy than `longest_first`, "
                "for instance `only_second` or `only_first`."
            )

        # Load from model defaults
        if return_token_type_ids is None:
            return_token_type_ids = "token_type_ids" in self.model_input_names
        if return_attention_mask is None:
            return_attention_mask = "attention_mask" in self.model_input_names

        encoded_inputs = {}

        # Compute the total size of the returned encodings
        total_len = (
            len_ids
            + len_pair_ids
            + (self.num_special_tokens_to_add(pair=pair) if add_special_tokens else 0)
        )

        # Truncation: Handle max sequence length
        overflowing_tokens = []
        if (
            truncation_strategy != TruncationStrategy.DO_NOT_TRUNCATE
            and max_length
            and total_len > max_length
        ):
            ids, pair_ids, overflowing_tokens = self.truncate_sequences(
                ids,
                pair_ids=pair_ids,
                num_tokens_to_remove=total_len - max_length,
                truncation_strategy=truncation_strategy,
                stride=stride,
            )
            shape_ids, pair_shape_ids, _ = self.truncate_sequences(
                shape_ids,
                pair_ids=pair_shape_ids,
                num_tokens_to_remove=total_len - max_length,
                truncation_strategy=truncation_strategy,
                stride=stride,
            )
            pronunciation_ids, pair_pronunciation_ids, _ = self.truncate_sequences(
                pronunciation_ids,
                pair_ids=pair_pronunciation_ids,
                num_tokens_to_remove=total_len - max_length,
                truncation_strategy=truncation_strategy,
                stride=stride,
            )

        if return_overflowing_tokens:
            encoded_inputs["overflowing_tokens"] = overflowing_tokens
            encoded_inputs["num_truncated_tokens"] = total_len - max_length

        # Add special tokens
        if add_special_tokens:
            sequence = self.build_inputs_with_special_tokens(ids, pair_ids)
            token_type_ids = self.create_token_type_ids_from_sequences(ids, pair_ids)
            input_shape_ids = self.build_inputs_with_special_tokens(
                shape_ids,
                pair_shape_ids,
                self.word_shape["[UNK]"],
                self.word_shape["[UNK]"],
            )
            input_pronunciation_ids = self.build_inputs_with_special_tokens(
                pronunciation_ids,
                pair_pronunciation_ids,
                self.word_pronunciation["[UNK]"],
                self.word_pronunciation["[UNK]"],
            )
        else:
            sequence = ids + pair_ids if pair_ids else ids
            token_type_ids = [0] * len(ids) + ([0] * len(pair_ids) if pair_ids else [])
            input_shape_ids = (
                shape_ids + pair_shape_ids if pair_shape_ids else shape_ids
            )
            input_pronunciation_ids = (
                pronunciation_ids + pair_pronunciation_ids
                if pair_pronunciation_ids
                else pronunciation_ids
            )

        # Build output dictionary
        encoded_inputs["input_ids"] = sequence
        encoded_inputs["input_shape_ids"] = input_shape_ids
        encoded_inputs["input_pronunciation_ids"] = input_pronunciation_ids
        if return_token_type_ids:
            encoded_inputs["token_type_ids"] = token_type_ids
        if return_special_tokens_mask:
            if add_special_tokens:
                encoded_inputs["special_tokens_mask"] = self.get_special_tokens_mask(
                    ids, pair_ids
                )
            else:
                encoded_inputs["special_tokens_mask"] = [0] * len(sequence)

        # Check lengths
        self._eventual_warn_about_too_long_sequence(
            encoded_inputs["input_ids"], max_length, verbose
        )

        # Padding
        if padding_strategy != PaddingStrategy.DO_NOT_PAD or return_attention_mask:
            encoded_inputs = self.pad(
                encoded_inputs,
                max_length=max_length,
                padding=padding_strategy.value,
                pad_to_multiple_of=pad_to_multiple_of,
                return_attention_mask=return_attention_mask,
            )

        if return_length:
            encoded_inputs["length"] = len(encoded_inputs["input_ids"])

        batch_outputs = BatchEncoding(
            encoded_inputs,
            tensor_type=return_tensors,
            prepend_batch_axis=prepend_batch_axis,
        )

        return batch_outputs

    def _pad(
        self,
        encoded_inputs: Union[Dict[str, EncodedInput], BatchEncoding],
        max_length: Optional[int] = None,
        padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
        pad_to_multiple_of: Optional[int] = None,
        return_attention_mask: Optional[bool] = None,
    ) -> dict:
        # Load from model defaults
        if return_attention_mask is None:
            return_attention_mask = "attention_mask" in self.model_input_names

        required_input = encoded_inputs[self.model_input_names[0]]

        if padding_strategy == PaddingStrategy.LONGEST:
            max_length = len(required_input)

        if (
            max_length is not None
            and pad_to_multiple_of is not None
            and (max_length % pad_to_multiple_of != 0)
        ):
            max_length = ((max_length // pad_to_multiple_of) + 1) * pad_to_multiple_of

        needs_to_be_padded = (
            padding_strategy != PaddingStrategy.DO_NOT_PAD
            and len(required_input) != max_length
        )

        # Initialize attention mask if not present.
        if return_attention_mask and "attention_mask" not in encoded_inputs:
            encoded_inputs["attention_mask"] = [1] * len(required_input)

        if needs_to_be_padded:
            difference = max_length - len(required_input)

            if self.padding_side == "right":
                if return_attention_mask:
                    encoded_inputs["attention_mask"] = (
                        encoded_inputs["attention_mask"] + [0] * difference
                    )
                if "token_type_ids" in encoded_inputs:
                    encoded_inputs["token_type_ids"] = (
                        encoded_inputs["token_type_ids"]
                        + [self.pad_token_type_id] * difference
                    )
                if "special_tokens_mask" in encoded_inputs:
                    encoded_inputs["special_tokens_mask"] = (
                        encoded_inputs["special_tokens_mask"] + [1] * difference
                    )
                for key in ["input_shape_ids", "input_pronunciation_ids"]:
                    if key in encoded_inputs:
                        encoded_inputs[key] = (
                            encoded_inputs[key] + [self.pad_token_id] * difference
                        )
                encoded_inputs[self.model_input_names[0]] = (
                    required_input + [self.pad_token_id] * difference
                )
            elif self.padding_side == "left":
                if return_attention_mask:
                    encoded_inputs["attention_mask"] = [
                        0
                    ] * difference + encoded_inputs["attention_mask"]
                if "token_type_ids" in encoded_inputs:
                    encoded_inputs["token_type_ids"] = [
                        self.pad_token_type_id
                    ] * difference + encoded_inputs["token_type_ids"]
                if "special_tokens_mask" in encoded_inputs:
                    encoded_inputs["special_tokens_mask"] = [
                        1
                    ] * difference + encoded_inputs["special_tokens_mask"]
                for key in ["input_shape_ids", "input_pronunciation_ids"]:
                    if key in encoded_inputs:
                        encoded_inputs[key] = [
                            self.pad_token_id
                        ] * difference + encoded_inputs[key]
                encoded_inputs[self.model_input_names[0]] = [
                    self.pad_token_id
                ] * difference + required_input
            else:
                raise ValueError("Invalid padding strategy:" + str(self.padding_side))

        return encoded_inputs

    def _batch_encode_plus(
        self,
        batch_text_or_text_pairs: Union[
            List[TextInput],
            List[TextInputPair],
            List[PreTokenizedInput],
            List[PreTokenizedInputPair],
            List[EncodedInput],
            List[EncodedInputPair],
        ],
        add_special_tokens: bool = True,
        padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
        truncation_strategy: TruncationStrategy = TruncationStrategy.DO_NOT_TRUNCATE,
        max_length: Optional[int] = None,
        stride: int = 0,
        is_split_into_words: bool = False,
        pad_to_multiple_of: Optional[int] = None,
        return_tensors: Optional[Union[str, TensorType]] = None,
        return_token_type_ids: Optional[bool] = None,
        return_attention_mask: Optional[bool] = None,
        return_overflowing_tokens: bool = False,
        return_special_tokens_mask: bool = False,
        return_offsets_mapping: bool = False,
        return_length: bool = False,
        verbose: bool = True,
        **kwargs,
    ) -> BatchEncoding:
        def get_input_ids(text):
            if isinstance(text, str):
                tokens = self.tokenize(text, **kwargs)
                tokens_ids = self.convert_tokens_to_ids(tokens)
                tokens_shape_ids = self.convert_tokens_to_shape_ids(tokens)
                tokens_proun_ids = self.convert_tokens_to_pronunciation_ids(tokens)
                return tokens_ids, tokens_shape_ids, tokens_proun_ids
            elif (
                isinstance(text, (list, tuple))
                and len(text) > 0
                and isinstance(text[0], str)
            ):
                if is_split_into_words:
                    tokens = list(
                        itertools.chain(
                            *(
                                self.tokenize(t, is_split_into_words=True, **kwargs)
                                for t in text
                            )
                        )
                    )
                    tokens_ids = self.convert_tokens_to_ids(tokens)
                    tokens_shape_ids = self.convert_tokens_to_shape_ids(tokens)
                    tokens_proun_ids = self.convert_tokens_to_pronunciation_ids(tokens)
                    return tokens_ids, tokens_shape_ids, tokens_proun_ids
                else:
                    tokens_ids = self.convert_tokens_to_ids(text)
                    tokens_shape_ids = self.convert_tokens_to_shape_ids(text)
                    tokens_proun_ids = self.convert_tokens_to_pronunciation_ids(text)
                    return tokens_ids, tokens_shape_ids, tokens_proun_ids
            elif (
                isinstance(text, (list, tuple))
                and len(text) > 0
                and isinstance(text[0], int)
            ):
                return (
                    text,
                    [0] * len(text),
                    [0] * len(text),
                )  # shape and proun id is pad_value
            else:
                raise ValueError(
                    "Input is not valid. Should be a string, a list/tuple of strings or a list/tuple of integers."
                )

        if return_offsets_mapping:
            raise NotImplementedError(
                "return_offset_mapping is not available when using Python tokenizers. "
                "To use this feature, change your tokenizer to one deriving from "
                "transformers.PreTrainedTokenizerFast."
            )

        input_ids = []
        input_shape_ids = []
        input_pronunciation_ids = []
        for ids_or_pair_ids in batch_text_or_text_pairs:
            if not isinstance(ids_or_pair_ids, (list, tuple)):
                ids, pair_ids = ids_or_pair_ids, None
            elif is_split_into_words and not isinstance(
                ids_or_pair_ids[0], (list, tuple)
            ):
                ids, pair_ids = ids_or_pair_ids, None
            else:
                ids, pair_ids = ids_or_pair_ids

            first_ids, first_shape_ids, first_proun_ids = get_input_ids(ids)
            if pair_ids is not None:
                second_ids, second_shape_ids, second_proun_ids = get_input_ids(pair_ids)
            else:
                second_ids, second_shape_ids, second_proun_ids = None, None, None

            input_ids.append((first_ids, second_ids))
            input_shape_ids.append((first_shape_ids, second_shape_ids))
            input_pronunciation_ids.append((first_proun_ids, second_proun_ids))

        batch_outputs = self._batch_prepare_for_model(
            input_ids,
            batch_shape_ids_pairs=input_shape_ids,
            batch_pronunciation_ids_pairs=input_pronunciation_ids,
            add_special_tokens=add_special_tokens,
            padding_strategy=padding_strategy,
            truncation_strategy=truncation_strategy,
            max_length=max_length,
            stride=stride,
            pad_to_multiple_of=pad_to_multiple_of,
            return_attention_mask=return_attention_mask,
            return_token_type_ids=return_token_type_ids,
            return_overflowing_tokens=return_overflowing_tokens,
            return_special_tokens_mask=return_special_tokens_mask,
            return_length=return_length,
            return_tensors=return_tensors,
            verbose=verbose,
        )

        return BatchEncoding(batch_outputs)

    def _batch_prepare_for_model(
        self,
        batch_ids_pairs: List[Union[PreTokenizedInputPair, Tuple[List[int], None]]],
        batch_shape_ids_pairs: List[
            Union[PreTokenizedInputPair, Tuple[List[int], None]]
        ],
        batch_pronunciation_ids_pairs: List[
            Union[PreTokenizedInputPair, Tuple[List[int], None]]
        ],
        add_special_tokens: bool = True,
        padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
        truncation_strategy: TruncationStrategy = TruncationStrategy.DO_NOT_TRUNCATE,
        max_length: Optional[int] = None,
        stride: int = 0,
        pad_to_multiple_of: Optional[int] = None,
        return_tensors: Optional[str] = None,
        return_token_type_ids: Optional[bool] = None,
        return_attention_mask: Optional[bool] = None,
        return_overflowing_tokens: bool = False,
        return_special_tokens_mask: bool = False,
        return_length: bool = False,
        verbose: bool = True,
    ) -> BatchEncoding:
        """
        Prepares a sequence of input id, or a pair of sequences of inputs ids so that it can be used by the model. It
        adds special tokens, truncates sequences if overflowing while taking into account the special tokens and
        manages a moving window (with user defined stride) for overflowing tokens

        Args:
            batch_ids_pairs: list of tokenized input ids or input ids pairs
            batch_shape_ids_pairs: list of tokenized input shape ids or input shape ids pairs
            batch_pronunciation_ids_pairs: list of tokenized input pronunciation ids or input pronunciation ids pairs
        """

        batch_outputs = {}
        for i, (first_ids, second_ids) in enumerate(batch_ids_pairs):
            first_shape_ids, second_shape_ids = batch_shape_ids_pairs[i]
            first_pronunciation_ids, second_pronunciation_ids = (
                batch_pronunciation_ids_pairs[i]
            )
            outputs = self.prepare_for_model(
                first_ids,
                first_shape_ids,
                first_pronunciation_ids,
                pair_ids=second_ids,
                pair_shape_ids=second_shape_ids,
                pair_pronunciation_ids=second_pronunciation_ids,
                add_special_tokens=add_special_tokens,
                padding=PaddingStrategy.DO_NOT_PAD.value,  # we pad in batch afterward
                truncation=truncation_strategy.value,
                max_length=max_length,
                stride=stride,
                pad_to_multiple_of=None,  # we pad in batch afterward
                return_attention_mask=False,  # we pad in batch afterward
                return_token_type_ids=return_token_type_ids,
                return_overflowing_tokens=return_overflowing_tokens,
                return_special_tokens_mask=return_special_tokens_mask,
                return_length=return_length,
                return_tensors=None,  # We convert the whole batch to tensors at the end
                prepend_batch_axis=False,
                verbose=verbose,
            )

            for key, value in outputs.items():
                if key not in batch_outputs:
                    batch_outputs[key] = []
                batch_outputs[key].append(value)

        batch_outputs = self.pad(
            batch_outputs,
            padding=padding_strategy.value,
            max_length=max_length,
            pad_to_multiple_of=pad_to_multiple_of,
            return_attention_mask=return_attention_mask,
        )

        batch_outputs = BatchEncoding(batch_outputs, tensor_type=return_tensors)

        return batch_outputs

    # Copied from transformers.models.bert.tokenization_bert.BertTokenizer._convert_token_to_id
    def _convert_token_to_id(self, token):
        """Converts a token (str) in an id using the vocab."""
        return self.vocab.get(token, self.vocab.get(self.unk_token))

    def _convert_token_to_shape_id(self, token):
        """Converts a token (str) in an shape_id using the shape vocab."""
        return self.word_shape.get(token, self.word_shape.get(self.unk_token))

    def convert_tokens_to_shape_ids(
        self, tokens: Union[str, List[str]]
    ) -> Union[int, List[int]]:
        if tokens is None:
            return None

        ids = []
        for token in tokens:
            ids.append(self._convert_token_to_shape_id(token))
        return ids

    def _convert_token_to_pronunciation_id(self, token):
        """Converts a token (str) in an shape_id using the shape vocab."""
        return self.word_pronunciation.get(
            token, self.word_pronunciation.get(self.unk_token)
        )

    def convert_tokens_to_pronunciation_ids(
        self, tokens: Union[str, List[str]]
    ) -> Union[int, List[int]]:
        if tokens is None:
            return None

        ids = []
        for token in tokens:
            ids.append(self._convert_token_to_pronunciation_id(token))
        return ids

    # Copied from transformers.models.bert.tokenization_bert.BertTokenizer._convert_id_to_token
    def _convert_id_to_token(self, index):
        """Converts an index (integer) in a token (str) using the vocab."""
        return self.ids_to_tokens.get(index, self.unk_token)

    # Copied from transformers.models.bert.tokenization_bert.BertTokenizer.convert_tokens_to_string
    def convert_tokens_to_string(self, tokens):
        """Converts a sequence of tokens (string) in a single string."""
        out_string = " ".join(tokens).replace(" ##", "").strip()
        return out_string

    def build_inputs_with_special_tokens(
        self,
        token_ids_0: List[int],
        token_ids_1: Optional[List[int]] = None,
        cls_token_id: int = None,
        sep_token_id: int = None,
    ) -> List[int]:
        """
        Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
        adding special tokens. A BERT sequence has the following format:

        - single sequence: `[CLS] X [SEP]`
        - pair of sequences: `[CLS] A [SEP] B [SEP]`

        Args:
            token_ids_0 (`List[int]`):
                List of IDs to which the special tokens will be added.
            token_ids_1 (`List[int]`, *optional*):
                Optional second list of IDs for sequence pairs.

        Returns:
            `List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
        """
        cls = [self.cls_token_id] if cls_token_id is None else [cls_token_id]
        sep = [self.sep_token_id] if sep_token_id is None else [sep_token_id]
        if token_ids_1 is None:
            return cls + token_ids_0 + sep
        return cls + token_ids_0 + sep + token_ids_1 + sep

    # Copied from transformers.models.bert.tokenization_bert.BertTokenizer.get_special_tokens_mask
    def get_special_tokens_mask(
        self,
        token_ids_0: List[int],
        token_ids_1: Optional[List[int]] = None,
        already_has_special_tokens: bool = False,
    ) -> List[int]:
        """
        Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
        special tokens using the tokenizer `prepare_for_model` method.

        Args:
            token_ids_0 (`List[int]`):
                List of IDs.
            token_ids_1 (`List[int]`, *optional*):
                Optional second list of IDs for sequence pairs.
            already_has_special_tokens (`bool`, *optional*, defaults to `False`):
                Whether or not the token list is already formatted with special tokens for the model.

        Returns:
            `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
        """

        if already_has_special_tokens:
            return super().get_special_tokens_mask(
                token_ids_0=token_ids_0,
                token_ids_1=token_ids_1,
                already_has_special_tokens=True,
            )

        if token_ids_1 is not None:
            return [1] + ([0] * len(token_ids_0)) + [1] + ([0] * len(token_ids_1)) + [1]
        return [1] + ([0] * len(token_ids_0)) + [1]

    # Copied from transformers.models.bert.tokenization_bert.BertTokenizer.create_token_type_ids_from_sequences
    def create_token_type_ids_from_sequences(
        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
    ) -> List[int]:
        """
        Create a mask from the two sequences passed to be used in a sequence-pair classification task. A BERT sequence
        pair mask has the following format:

        ```
        0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1
        | first sequence    | second sequence |
        ```

        If `token_ids_1` is `None`, this method only returns the first portion of the mask (0s).

        Args:
            token_ids_0 (`List[int]`):
                List of IDs.
            token_ids_1 (`List[int]`, *optional*):
                Optional second list of IDs for sequence pairs.

        Returns:
            `List[int]`: List of [token type IDs](../glossary#token-type-ids) according to the given sequence(s).
        """
        sep = [self.sep_token_id]
        cls = [self.cls_token_id]
        if token_ids_1 is None:
            return len(cls + token_ids_0 + sep) * [0]
        return len(cls + token_ids_0 + sep) * [0] + len(token_ids_1 + sep) * [1]

    def save_vocabulary(
        self, save_directory: str, filename_prefix: Optional[str] = None
    ) -> Tuple[str, str, str]:
        index = 0
        if os.path.isdir(save_directory):
            vocab_file = os.path.join(
                save_directory,
                (filename_prefix + "-" if filename_prefix else "")
                + self.vocab_files_names["vocab_file"],
            )
            word_shape_file = os.path.join(
                save_directory,
                (filename_prefix + "-" if filename_prefix else "")
                + self.vocab_files_names["word_shape_file"],
            )
            word_pronunciation_file = os.path.join(
                save_directory,
                (filename_prefix + "-" if filename_prefix else "")
                + self.vocab_files_names["word_pronunciation_file"],
            )
        else:
            raise ValueError(
                f"Can't find a directory at path '{save_directory}'. To load the vocabulary from a Google "
                "pretrained model use `tokenizer = RoCBertTokenizer.from_pretrained(PRETRAINED_MODEL_NAME)`"
            )

        with open(vocab_file, "w", encoding="utf-8") as writer:
            for token, token_index in sorted(self.vocab.items(), key=lambda kv: kv[1]):
                if index != token_index:
                    logger.warning(
                        f"Saving vocabulary to {vocab_file}: vocabulary indices are not consecutive."
                        " Please check that the vocabulary is not corrupted!"
                    )
                    index = token_index
                writer.write(token + "\n")
                index += 1

        with open(word_shape_file, "w", encoding="utf8") as writer:
            json.dump(
                self.word_shape,
                writer,
                ensure_ascii=False,
                indent=4,
                separators=(", ", ": "),
            )

        with open(word_pronunciation_file, "w", encoding="utf8") as writer:
            json.dump(
                self.word_pronunciation,
                writer,
                ensure_ascii=False,
                indent=4,
                separators=(", ", ": "),
            )

        return (
            vocab_file,
            word_shape_file,
            word_pronunciation_file,
        )

mindnlp.transformers.models.roc_bert.tokenization_roc_bert.RoCBertTokenizer.build_inputs_with_special_tokens(token_ids_0, token_ids_1=None, cls_token_id=None, sep_token_id=None)

Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens. A BERT sequence has the following format:

  • single sequence: [CLS] X [SEP]
  • pair of sequences: [CLS] A [SEP] B [SEP]
PARAMETER DESCRIPTION
token_ids_0

List of IDs to which the special tokens will be added.

TYPE: `List[int]`

token_ids_1

Optional second list of IDs for sequence pairs.

TYPE: `List[int]`, *optional* DEFAULT: None

RETURNS DESCRIPTION
List[int]

List[int]: List of input IDs with the appropriate special tokens.
Source code in mindnlp/transformers/models/roc_bert/tokenization_roc_bert.py 
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
def build_inputs_with_special_tokens(
    self,
    token_ids_0: List[int],
    token_ids_1: Optional[List[int]] = None,
    cls_token_id: int = None,
    sep_token_id: int = None,
) -> List[int]:
    """
    Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
    adding special tokens. A BERT sequence has the following format:

    - single sequence: `[CLS] X [SEP]`
    - pair of sequences: `[CLS] A [SEP] B [SEP]`

    Args:
        token_ids_0 (`List[int]`):
            List of IDs to which the special tokens will be added.
        token_ids_1 (`List[int]`, *optional*):
            Optional second list of IDs for sequence pairs.

    Returns:
        `List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
    """
    cls = [self.cls_token_id] if cls_token_id is None else [cls_token_id]
    sep = [self.sep_token_id] if sep_token_id is None else [sep_token_id]
    if token_ids_1 is None:
        return cls + token_ids_0 + sep
    return cls + token_ids_0 + sep + token_ids_1 + sep

mindnlp.transformers.models.roc_bert.tokenization_roc_bert.RoCBertTokenizer.convert_tokens_to_string(tokens)

Converts a sequence of tokens (string) in a single string.

Source code in mindnlp/transformers/models/roc_bert/tokenization_roc_bert.py 
857
858
859
860
def convert_tokens_to_string(self, tokens):
    """Converts a sequence of tokens (string) in a single string."""
    out_string = " ".join(tokens).replace(" ##", "").strip()
    return out_string

mindnlp.transformers.models.roc_bert.tokenization_roc_bert.RoCBertTokenizer.create_token_type_ids_from_sequences(token_ids_0, token_ids_1=None)

Create a mask from the two sequences passed to be used in a sequence-pair classification task. A BERT sequence pair mask has the following format:

0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1
| first sequence    | second sequence |

If token_ids_1 is None, this method only returns the first portion of the mask (0s).

PARAMETER DESCRIPTION
token_ids_0

List of IDs.

TYPE: `List[int]`

token_ids_1

Optional second list of IDs for sequence pairs.

TYPE: `List[int]`, *optional* DEFAULT: None

RETURNS DESCRIPTION
List[int]

List[int]: List of token type IDs according to the given sequence(s).
Source code in mindnlp/transformers/models/roc_bert/tokenization_roc_bert.py 
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
def create_token_type_ids_from_sequences(
    self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
) -> List[int]:
    """
    Create a mask from the two sequences passed to be used in a sequence-pair classification task. A BERT sequence
    pair mask has the following format:

    ```
    0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1
    | first sequence    | second sequence |
    ```

    If `token_ids_1` is `None`, this method only returns the first portion of the mask (0s).

    Args:
        token_ids_0 (`List[int]`):
            List of IDs.
        token_ids_1 (`List[int]`, *optional*):
            Optional second list of IDs for sequence pairs.

    Returns:
        `List[int]`: List of [token type IDs](../glossary#token-type-ids) according to the given sequence(s).
    """
    sep = [self.sep_token_id]
    cls = [self.cls_token_id]
    if token_ids_1 is None:
        return len(cls + token_ids_0 + sep) * [0]
    return len(cls + token_ids_0 + sep) * [0] + len(token_ids_1 + sep) * [1]

mindnlp.transformers.models.roc_bert.tokenization_roc_bert.RoCBertTokenizer.get_special_tokens_mask(token_ids_0, token_ids_1=None, already_has_special_tokens=False)

Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding special tokens using the tokenizer prepare_for_model method.

PARAMETER DESCRIPTION
token_ids_0

List of IDs.

TYPE: `List[int]`

token_ids_1

Optional second list of IDs for sequence pairs.

TYPE: `List[int]`, *optional* DEFAULT: None

already_has_special_tokens

Whether or not the token list is already formatted with special tokens for the model.

TYPE: `bool`, *optional*, defaults to `False` DEFAULT: False

RETURNS DESCRIPTION
List[int]

List[int]: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
Source code in mindnlp/transformers/models/roc_bert/tokenization_roc_bert.py 
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
def get_special_tokens_mask(
    self,
    token_ids_0: List[int],
    token_ids_1: Optional[List[int]] = None,
    already_has_special_tokens: bool = False,
) -> List[int]:
    """
    Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
    special tokens using the tokenizer `prepare_for_model` method.

    Args:
        token_ids_0 (`List[int]`):
            List of IDs.
        token_ids_1 (`List[int]`, *optional*):
            Optional second list of IDs for sequence pairs.
        already_has_special_tokens (`bool`, *optional*, defaults to `False`):
            Whether or not the token list is already formatted with special tokens for the model.

    Returns:
        `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
    """

    if already_has_special_tokens:
        return super().get_special_tokens_mask(
            token_ids_0=token_ids_0,
            token_ids_1=token_ids_1,
            already_has_special_tokens=True,
        )

    if token_ids_1 is not None:
        return [1] + ([0] * len(token_ids_0)) + [1] + ([0] * len(token_ids_1)) + [1]
    return [1] + ([0] * len(token_ids_0)) + [1]

mindnlp.transformers.models.roc_bert.tokenization_roc_bert.RoCBertTokenizer.prepare_for_model(ids, shape_ids, pronunciation_ids, pair_ids=None, pair_shape_ids=None, pair_pronunciation_ids=None, add_special_tokens=True, padding=False, truncation=None, max_length=None, stride=0, pad_to_multiple_of=None, return_tensors=None, return_token_type_ids=None, return_attention_mask=None, return_overflowing_tokens=False, return_special_tokens_mask=False, return_offsets_mapping=False, return_length=False, verbose=True, prepend_batch_axis=False, **kwargs)

Prepares a sequence of input id, or a pair of sequences of inputs ids so that it can be used by the model. It adds special tokens, truncates sequences if overflowing while taking into account the special tokens and manages a moving window (with user defined stride) for overflowing tokens. Please Note, for pair_ids different than None and truncation_strategy = longest_first or True, it is not possible to return overflowing tokens. Such a combination of arguments will raise an error.

PARAMETER DESCRIPTION
ids

Tokenized input ids of the first sequence. Can be obtained from a string by chaining the tokenize and convert_tokens_to_id methods.

TYPE: `List[int]`

shape_ids

Tokenized input ids of the first sequence. Can be obtained from a string by chaining the tokenize and convert_token_to_shape_id methods.

TYPE: `List[int]`

pronunciation_ids

Tokenized input ids of the first sequence. Can be obtained from a string by chaining the tokenize and convert_token_to_pronunciation_id methods.

TYPE: `List[int]`

pair_ids

Tokenized input ids of the second sequence. Can be obtained from a string by chaining the tokenize and convert_tokens_to_id methods.

TYPE: `List[int]`, *optional* DEFAULT: None

pair_shape_ids

Tokenized input ids of the second sequence. Can be obtained from a string by chaining the tokenize and convert_token_to_shape_id methods.

TYPE: `List[int]`, *optional* DEFAULT: None

pair_pronunciation_ids

Tokenized input ids of the second sequence. Can be obtained from a string by chaining the tokenize and convert_token_to_pronunciation_id methods.

TYPE: `List[int]`, *optional* DEFAULT: None

Source code in mindnlp/transformers/models/roc_bert/tokenization_roc_bert.py 
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
def prepare_for_model(
    self,
    ids: List[int],
    shape_ids: List[int],
    pronunciation_ids: List[int],
    pair_ids: Optional[List[int]] = None,
    pair_shape_ids: Optional[List[int]] = None,
    pair_pronunciation_ids: Optional[List[int]] = None,
    add_special_tokens: bool = True,
    padding: Union[bool, str, PaddingStrategy] = False,
    truncation: Union[bool, str, TruncationStrategy] = None,
    max_length: Optional[int] = None,
    stride: int = 0,
    pad_to_multiple_of: Optional[int] = None,
    return_tensors: Optional[Union[str, TensorType]] = None,
    return_token_type_ids: Optional[bool] = None,
    return_attention_mask: Optional[bool] = None,
    return_overflowing_tokens: bool = False,
    return_special_tokens_mask: bool = False,
    return_offsets_mapping: bool = False,
    return_length: bool = False,
    verbose: bool = True,
    prepend_batch_axis: bool = False,
    **kwargs,
) -> BatchEncoding:
    """
    Prepares a sequence of input id, or a pair of sequences of inputs ids so that it can be used by the model. It
    adds special tokens, truncates sequences if overflowing while taking into account the special tokens and
    manages a moving window (with user defined stride) for overflowing tokens. Please Note, for *pair_ids*
    different than `None` and *truncation_strategy = longest_first* or `True`, it is not possible to return
    overflowing tokens. Such a combination of arguments will raise an error.

    Args:
        ids (`List[int]`):
            Tokenized input ids of the first sequence. Can be obtained from a string by chaining the `tokenize` and
            `convert_tokens_to_id` methods.
        shape_ids (`List[int]`):
            Tokenized input ids of the first sequence. Can be obtained from a string by chaining the `tokenize` and
            `convert_token_to_shape_id` methods.
        pronunciation_ids (`List[int]`):
            Tokenized input ids of the first sequence. Can be obtained from a string by chaining the `tokenize` and
            `convert_token_to_pronunciation_id` methods.
        pair_ids (`List[int]`, *optional*):
            Tokenized input ids of the second sequence. Can be obtained from a string by chaining the `tokenize`
            and `convert_tokens_to_id` methods.
        pair_shape_ids (`List[int]`, *optional*):
            Tokenized input ids of the second sequence. Can be obtained from a string by chaining the `tokenize`
            and `convert_token_to_shape_id` methods.
        pair_pronunciation_ids (`List[int]`, *optional*):
            Tokenized input ids of the second sequence. Can be obtained from a string by chaining the `tokenize`
            and `convert_token_to_pronunciation_id` methods.
    """

    # Backward compatibility for 'truncation_strategy', 'pad_to_max_length'
    padding_strategy, truncation_strategy, max_length, kwargs = (
        self._get_padding_truncation_strategies(
            padding=padding,
            truncation=truncation,
            max_length=max_length,
            pad_to_multiple_of=pad_to_multiple_of,
            verbose=verbose,
            **kwargs,
        )
    )

    pair = bool(pair_ids is not None)
    len_ids = len(ids)
    len_pair_ids = len(pair_ids) if pair else 0

    if return_token_type_ids and not add_special_tokens:
        raise ValueError(
            "Asking to return token_type_ids while setting add_special_tokens to False "
            "results in an undefined behavior. Please set add_special_tokens to True or "
            "set return_token_type_ids to None."
        )

    if (
        return_overflowing_tokens
        and truncation_strategy == TruncationStrategy.LONGEST_FIRST
        and pair_ids is not None
    ):
        raise ValueError(
            "Not possible to return overflowing tokens for pair of sequences with the "
            "`longest_first`. Please select another truncation strategy than `longest_first`, "
            "for instance `only_second` or `only_first`."
        )

    # Load from model defaults
    if return_token_type_ids is None:
        return_token_type_ids = "token_type_ids" in self.model_input_names
    if return_attention_mask is None:
        return_attention_mask = "attention_mask" in self.model_input_names

    encoded_inputs = {}

    # Compute the total size of the returned encodings
    total_len = (
        len_ids
        + len_pair_ids
        + (self.num_special_tokens_to_add(pair=pair) if add_special_tokens else 0)
    )

    # Truncation: Handle max sequence length
    overflowing_tokens = []
    if (
        truncation_strategy != TruncationStrategy.DO_NOT_TRUNCATE
        and max_length
        and total_len > max_length
    ):
        ids, pair_ids, overflowing_tokens = self.truncate_sequences(
            ids,
            pair_ids=pair_ids,
            num_tokens_to_remove=total_len - max_length,
            truncation_strategy=truncation_strategy,
            stride=stride,
        )
        shape_ids, pair_shape_ids, _ = self.truncate_sequences(
            shape_ids,
            pair_ids=pair_shape_ids,
            num_tokens_to_remove=total_len - max_length,
            truncation_strategy=truncation_strategy,
            stride=stride,
        )
        pronunciation_ids, pair_pronunciation_ids, _ = self.truncate_sequences(
            pronunciation_ids,
            pair_ids=pair_pronunciation_ids,
            num_tokens_to_remove=total_len - max_length,
            truncation_strategy=truncation_strategy,
            stride=stride,
        )

    if return_overflowing_tokens:
        encoded_inputs["overflowing_tokens"] = overflowing_tokens
        encoded_inputs["num_truncated_tokens"] = total_len - max_length

    # Add special tokens
    if add_special_tokens:
        sequence = self.build_inputs_with_special_tokens(ids, pair_ids)
        token_type_ids = self.create_token_type_ids_from_sequences(ids, pair_ids)
        input_shape_ids = self.build_inputs_with_special_tokens(
            shape_ids,
            pair_shape_ids,
            self.word_shape["[UNK]"],
            self.word_shape["[UNK]"],
        )
        input_pronunciation_ids = self.build_inputs_with_special_tokens(
            pronunciation_ids,
            pair_pronunciation_ids,
            self.word_pronunciation["[UNK]"],
            self.word_pronunciation["[UNK]"],
        )
    else:
        sequence = ids + pair_ids if pair_ids else ids
        token_type_ids = [0] * len(ids) + ([0] * len(pair_ids) if pair_ids else [])
        input_shape_ids = (
            shape_ids + pair_shape_ids if pair_shape_ids else shape_ids
        )
        input_pronunciation_ids = (
            pronunciation_ids + pair_pronunciation_ids
            if pair_pronunciation_ids
            else pronunciation_ids
        )

    # Build output dictionary
    encoded_inputs["input_ids"] = sequence
    encoded_inputs["input_shape_ids"] = input_shape_ids
    encoded_inputs["input_pronunciation_ids"] = input_pronunciation_ids
    if return_token_type_ids:
        encoded_inputs["token_type_ids"] = token_type_ids
    if return_special_tokens_mask:
        if add_special_tokens:
            encoded_inputs["special_tokens_mask"] = self.get_special_tokens_mask(
                ids, pair_ids
            )
        else:
            encoded_inputs["special_tokens_mask"] = [0] * len(sequence)

    # Check lengths
    self._eventual_warn_about_too_long_sequence(
        encoded_inputs["input_ids"], max_length, verbose
    )

    # Padding
    if padding_strategy != PaddingStrategy.DO_NOT_PAD or return_attention_mask:
        encoded_inputs = self.pad(
            encoded_inputs,
            max_length=max_length,
            padding=padding_strategy.value,
            pad_to_multiple_of=pad_to_multiple_of,
            return_attention_mask=return_attention_mask,
        )

    if return_length:
        encoded_inputs["length"] = len(encoded_inputs["input_ids"])

    batch_outputs = BatchEncoding(
        encoded_inputs,
        tensor_type=return_tensors,
        prepend_batch_axis=prepend_batch_axis,
    )

    return batch_outputs

mindnlp.transformers.models.roc_bert.tokenization_roc_bert.RoCBertWordpieceTokenizer

Runs WordPiece tokenization.

Source code in mindnlp/transformers/models/roc_bert/tokenization_roc_bert.py 
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
class RoCBertWordpieceTokenizer:
    """Runs WordPiece tokenization."""

    def __init__(self, vocab, unk_token, max_input_chars_per_word=100):
        self.vocab = vocab
        self.unk_token = unk_token
        self.max_input_chars_per_word = max_input_chars_per_word

    def tokenize(self, text):
        """
        Tokenizes a piece of text into its word pieces. This uses a greedy longest-match-first algorithm to perform
        tokenization using the given vocabulary.

        For example, `input = "unaffable"` wil return as output `["un", "##aff", "##able"]`.

        Args:
            text: A single token or whitespace separated tokens. This should have
                already been passed through *BasicTokenizer*.

        Returns:
            A list of wordpiece tokens.
        """

        output_tokens = []
        for token in whitespace_tokenize(text):
            chars = list(token)
            if len(chars) > self.max_input_chars_per_word:
                output_tokens.append(self.unk_token)
                continue

            is_bad = False
            start = 0
            sub_tokens = []
            while start < len(chars):
                end = len(chars)
                cur_substr = None
                while start < end:
                    substr = "".join(chars[start:end])
                    if start > 0:
                        substr = "##" + substr
                    if substr in self.vocab:
                        cur_substr = substr
                        break
                    end -= 1
                if cur_substr is None:
                    is_bad = True
                    break
                sub_tokens.append(cur_substr)
                start = end

            if is_bad:
                output_tokens.append(self.unk_token)
            else:
                output_tokens.extend(sub_tokens)
        return output_tokens

mindnlp.transformers.models.roc_bert.tokenization_roc_bert.RoCBertWordpieceTokenizer.tokenize(text)

Tokenizes a piece of text into its word pieces. This uses a greedy longest-match-first algorithm to perform tokenization using the given vocabulary.

For example, input = "unaffable" wil return as output ["un", "##aff", "##able"].

PARAMETER DESCRIPTION
text

A single token or whitespace separated tokens. This should have already been passed through BasicTokenizer.
RETURNS DESCRIPTION

A list of wordpiece tokens.
Source code in mindnlp/transformers/models/roc_bert/tokenization_roc_bert.py 
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
def tokenize(self, text):
    """
    Tokenizes a piece of text into its word pieces. This uses a greedy longest-match-first algorithm to perform
    tokenization using the given vocabulary.

    For example, `input = "unaffable"` wil return as output `["un", "##aff", "##able"]`.

    Args:
        text: A single token or whitespace separated tokens. This should have
            already been passed through *BasicTokenizer*.

    Returns:
        A list of wordpiece tokens.
    """

    output_tokens = []
    for token in whitespace_tokenize(text):
        chars = list(token)
        if len(chars) > self.max_input_chars_per_word:
            output_tokens.append(self.unk_token)
            continue

        is_bad = False
        start = 0
        sub_tokens = []
        while start < len(chars):
            end = len(chars)
            cur_substr = None
            while start < end:
                substr = "".join(chars[start:end])
                if start > 0:
                    substr = "##" + substr
                if substr in self.vocab:
                    cur_substr = substr
                    break
                end -= 1
            if cur_substr is None:
                is_bad = True
                break
            sub_tokens.append(cur_substr)
            start = end

        if is_bad:
            output_tokens.append(self.unk_token)
        else:
            output_tokens.extend(sub_tokens)
    return output_tokens

mindnlp.transformers.models.roc_bert.tokenization_roc_bert.load_vocab(vocab_file)

Loads a vocabulary file into a dictionary.

Source code in mindnlp/transformers/models/roc_bert/tokenization_roc_bert.py 
55
56
57
58
59
60
61
62
63
def load_vocab(vocab_file):
    """Loads a vocabulary file into a dictionary."""
    vocab = collections.OrderedDict()
    with open(vocab_file, "r", encoding="utf-8") as reader:
        tokens = reader.readlines()
    for index, token in enumerate(tokens):
        token = token.rstrip("\n")
        vocab[token] = index
    return vocab

mindnlp.transformers.models.roc_bert.tokenization_roc_bert.whitespace_tokenize(text)

Runs basic whitespace cleaning and splitting on a piece of text.

Source code in mindnlp/transformers/models/roc_bert/tokenization_roc_bert.py 
67
68
69
70
71
72
73
def whitespace_tokenize(text):
    """Runs basic whitespace cleaning and splitting on a piece of text."""
    text = text.strip()
    if not text:
        return []
    tokens = text.split()
    return tokens