nystromformer

mindnlp.transformers.models.nystromformer.configuration_nystromformer

Nystromformer model configuration

mindnlp.transformers.models.nystromformer.configuration_nystromformer.NystromformerConfig

Bases: PretrainedConfig

This is the configuration class to store the configuration of a [NystromformerModel]. It is used to instantiate an Nystromformer 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 Nystromformer uw-madison/nystromformer-512 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 Nystromformer model. Defines the number of different tokens that can be represented by the inputs_ids passed when calling [NystromformerModel]. TYPE: `int`, *optional*, defaults to 30000 DEFAULT: 30000
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_new'
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: 510
type_vocab_size	The vocabulary size of the token_type_ids passed when calling [NystromformerModel]. TYPE: `int`, *optional*, defaults to 2 DEFAULT: 2
segment_means_seq_len	Sequence length used in segment-means. TYPE: `int`, *optional*, defaults to 64 DEFAULT: 64
num_landmarks	The number of landmark (or Nystrom) points to use in Nystrom approximation of the softmax self-attention matrix. TYPE: `int`, *optional*, defaults to 64 DEFAULT: 64
conv_kernel_size	The kernel size of depthwise convolution used in Nystrom approximation. TYPE: `int`, *optional*, defaults to 65 DEFAULT: 65
inv_coeff_init_option	Whether or not to use exact coefficient computation for the initial values for the iterative method of calculating the Moore-Penrose inverse of a matrix. TYPE: `bool`, *optional*, defaults to `False` DEFAULT: False
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-05

Example

>>> from transformers import NystromformerModel, NystromformerConfig
...
>>> # Initializing a Nystromformer uw-madison/nystromformer-512 style configuration
>>> configuration = NystromformerConfig()
...
>>> # Initializing a model from the uw-madison/nystromformer-512 style configuration
>>> model = NystromformerModel(configuration)
...
>>> # Accessing the model configuration
>>> configuration = model.config

Source code in mindnlp/transformers/models/nystromformer/configuration_nystromformer.py

class NystromformerConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`NystromformerModel`]. It is used to instantiate
    an Nystromformer 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 Nystromformer
    [uw-madison/nystromformer-512](https://huggingface.co/uw-madison/nystromformer-512) 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 30000):
            Vocabulary size of the Nystromformer model. Defines the number of different tokens that can be represented
            by the `inputs_ids` passed when calling [`NystromformerModel`].
        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 [`NystromformerModel`].
        segment_means_seq_len (`int`, *optional*, defaults to 64):
            Sequence length used in segment-means.
        num_landmarks (`int`, *optional*, defaults to 64):
            The number of landmark (or Nystrom) points to use in Nystrom approximation of the softmax self-attention
            matrix.
        conv_kernel_size (`int`, *optional*, defaults to 65):
            The kernel size of depthwise convolution used in Nystrom approximation.
        inv_coeff_init_option (`bool`, *optional*, defaults to `False`):
            Whether or not to use exact coefficient computation for the initial values for the iterative method of
            calculating the Moore-Penrose inverse of a matrix.
        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.

    Example:
        ```python
        >>> from transformers import NystromformerModel, NystromformerConfig
        ...
        >>> # Initializing a Nystromformer uw-madison/nystromformer-512 style configuration
        >>> configuration = NystromformerConfig()
        ...
        >>> # Initializing a model from the uw-madison/nystromformer-512 style configuration
        >>> model = NystromformerModel(configuration)
        ...
        >>> # Accessing the model configuration
        >>> configuration = model.config
        ```
    """

    model_type = "nystromformer"

    def __init__(
        self,
        vocab_size=30000,
        hidden_size=768,
        num_hidden_layers=12,
        num_attention_heads=12,
        intermediate_size=3072,
        hidden_act="gelu_new",
        hidden_dropout_prob=0.1,
        attention_probs_dropout_prob=0.1,
        max_position_embeddings=510,
        type_vocab_size=2,
        segment_means_seq_len=64,
        num_landmarks=64,
        conv_kernel_size=65,
        inv_coeff_init_option=False,
        initializer_range=0.02,
        layer_norm_eps=1e-5,
        pad_token_id=1,
        bos_token_id=0,
        eos_token_id=2,
        **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.segment_means_seq_len = segment_means_seq_len
        self.num_landmarks = num_landmarks
        self.conv_kernel_size = conv_kernel_size
        self.inv_coeff_init_option = inv_coeff_init_option
        self.layer_norm_eps = layer_norm_eps
        super().__init__(pad_token_id=pad_token_id, bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs)

mindnlp.transformers.models.nystromformer.modeling_nystromformer

PyTorch Nystromformer model.

mindnlp.transformers.models.nystromformer.modeling_nystromformer.NystromformerClassificationHead

Bases: Module

Head for sentence-level classification tasks.

Source code in mindnlp/transformers/models/nystromformer/modeling_nystromformer.py

class NystromformerClassificationHead(nn.Module):
    """Head for sentence-level classification tasks."""

    def __init__(self, config):
        super().__init__()
        self.dense = nn.Linear(config.hidden_size, config.hidden_size)
        self.dropout = nn.Dropout(p=config.hidden_dropout_prob)
        self.out_proj = nn.Linear(config.hidden_size, config.num_labels)

        self.config = config

    def forward(self, features, **kwargs):
        x = features[:, 0, :]  # take <s> token (equiv. to [CLS])
        x = self.dropout(x)
        x = self.dense(x)
        x = ACT2FN[self.config.hidden_act](x)
        x = self.dropout(x)
        x = self.out_proj(x)
        return x

mindnlp.transformers.models.nystromformer.modeling_nystromformer.NystromformerEmbeddings

Bases: Module

Construct the embeddings from word, position and token_type embeddings.

Source code in mindnlp/transformers/models/nystromformer/modeling_nystromformer.py

class NystromformerEmbeddings(nn.Module):
    """Construct the embeddings from word, position 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.position_embeddings = nn.Embedding(config.max_position_embeddings + 2, config.hidden_size)
        self.token_type_embeddings = nn.Embedding(config.type_vocab_size, config.hidden_size)

        # 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).expand((1, -1)) + 2
        self.position_embedding_type = getattr(config, "position_embedding_type", "absolute")
        self.token_type_ids=ops.zeros(self.position_ids.shape, dtype=mstype.int64)

    def forward(self, input_ids=None, token_type_ids=None, position_ids=None, inputs_embeds=None):
        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[:, :seq_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.expand(input_shape[0], seq_length)
                token_type_ids = buffered_token_type_ids_expanded
            else:
                token_type_ids = ops.zeros(input_shape, dtype=mstype.int64)

        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)
        return embeddings

mindnlp.transformers.models.nystromformer.modeling_nystromformer.NystromformerForMaskedLM

Bases: NystromformerPreTrainedModel

Source code in mindnlp/transformers/models/nystromformer/modeling_nystromformer.py

class NystromformerForMaskedLM(NystromformerPreTrainedModel):
    _tied_weights_keys = ["cls.predictions.decoder"]

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

        self.nystromformer = NystromformerModel(config)
        self.cls = NystromformerOnlyMLMHead(config)

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

    def get_output_embeddings(self):
        return self.cls.predictions.decoder

    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,
        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], MaskedLMOutput]:
        r"""
        Args:
            labels (`mindspore.Tensor` 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]`.
        """
        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        outputs = self.nystromformer(
            input_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]
        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[1:]
            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.nystromformer.modeling_nystromformer.NystromformerForMaskedLM.forward(input_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 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: `mindspore.Tensor` of shape `(batch_size, sequence_length)`, *optional* DEFAULT: None

Source code in mindnlp/transformers/models/nystromformer/modeling_nystromformer.py

def forward(
    self,
    input_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], MaskedLMOutput]:
    r"""
    Args:
        labels (`mindspore.Tensor` 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]`.
    """
    return_dict = return_dict if return_dict is not None else self.config.use_return_dict

    outputs = self.nystromformer(
        input_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]
    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[1:]
        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.nystromformer.modeling_nystromformer.NystromformerForMultipleChoice

Bases: NystromformerPreTrainedModel

Source code in mindnlp/transformers/models/nystromformer/modeling_nystromformer.py

class NystromformerForMultipleChoice(NystromformerPreTrainedModel):
    def __init__(self, config):
        super().__init__(config)

        self.nystromformer = NystromformerModel(config)
        self.pre_classifier = nn.Linear(config.hidden_size, config.hidden_size)
        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,
        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 (`mindspore.Tensor` 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
        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.nystromformer(
            input_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,
        )

        hidden_state = outputs[0]  # (bs * num_choices, seq_len, dim)
        pooled_output = hidden_state[:, 0]  # (bs * num_choices, dim)
        pooled_output = self.pre_classifier(pooled_output)  # (bs * num_choices, dim)
        pooled_output = nn.ReLU()(pooled_output)  # (bs * num_choices, dim)
        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[1:]
            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.nystromformer.modeling_nystromformer.NystromformerForMultipleChoice.forward(input_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: `mindspore.Tensor` of shape `(batch_size,)`, *optional* DEFAULT: None

Source code in mindnlp/transformers/models/nystromformer/modeling_nystromformer.py

def forward(
    self,
    input_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 (`mindspore.Tensor` 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
    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.nystromformer(
        input_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,
    )

    hidden_state = outputs[0]  # (bs * num_choices, seq_len, dim)
    pooled_output = hidden_state[:, 0]  # (bs * num_choices, dim)
    pooled_output = self.pre_classifier(pooled_output)  # (bs * num_choices, dim)
    pooled_output = nn.ReLU()(pooled_output)  # (bs * num_choices, dim)
    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[1:]
        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.nystromformer.modeling_nystromformer.NystromformerForQuestionAnswering

Bases: NystromformerPreTrainedModel

Source code in mindnlp/transformers/models/nystromformer/modeling_nystromformer.py

class NystromformerForQuestionAnswering(NystromformerPreTrainedModel):
    def __init__(self, config):
        super().__init__(config)

        config.num_labels = 2
        self.num_labels = config.num_labels

        self.nystromformer = NystromformerModel(config)
        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,
        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 (`mindspore.Tensor` 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 (`mindspore.Tensor` 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.nystromformer(
            input_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[1:]
            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.nystromformer.modeling_nystromformer.NystromformerForQuestionAnswering.forward(input_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: `mindspore.Tensor` 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: `mindspore.Tensor` of shape `(batch_size,)`, *optional* DEFAULT: None

Source code in mindnlp/transformers/models/nystromformer/modeling_nystromformer.py

def forward(
    self,
    input_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 (`mindspore.Tensor` 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 (`mindspore.Tensor` 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.nystromformer(
        input_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[1:]
        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.nystromformer.modeling_nystromformer.NystromformerForSequenceClassification

Bases: NystromformerPreTrainedModel

Source code in mindnlp/transformers/models/nystromformer/modeling_nystromformer.py

class NystromformerForSequenceClassification(NystromformerPreTrainedModel):
    def __init__(self, config):
        super().__init__(config)
        self.num_labels = config.num_labels
        self.nystromformer = NystromformerModel(config)
        self.classifier = NystromformerClassificationHead(config)

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

    def forward(
        self,
        input_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 (`mindspore.Tensor` 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.nystromformer(
            input_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.classifier(sequence_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 (mstype.int64, mstype.int32)):
                    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(logits.squeeze(), labels.squeeze())
                else:
                    loss = ops.mse(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_fct = mindspore.nn.BCEWithLogitsLoss()
                loss = loss_fct(logits, labels)
        if not return_dict:
            output = (logits,) + outputs[1:]
            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.nystromformer.modeling_nystromformer.NystromformerForSequenceClassification.forward(input_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: `mindspore.Tensor` of shape `(batch_size,)`, *optional* DEFAULT: None

Source code in mindnlp/transformers/models/nystromformer/modeling_nystromformer.py

def forward(
    self,
    input_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 (`mindspore.Tensor` 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.nystromformer(
        input_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.classifier(sequence_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 (mstype.int64, mstype.int32)):
                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(logits.squeeze(), labels.squeeze())
            else:
                loss = ops.mse(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_fct = mindspore.nn.BCEWithLogitsLoss()
            loss = loss_fct(logits, labels)
    if not return_dict:
        output = (logits,) + outputs[1:]
        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.nystromformer.modeling_nystromformer.NystromformerForTokenClassification

Bases: NystromformerPreTrainedModel

Source code in mindnlp/transformers/models/nystromformer/modeling_nystromformer.py

class NystromformerForTokenClassification(NystromformerPreTrainedModel):
    def __init__(self, config):
        super().__init__(config)
        self.num_labels = config.num_labels

        self.nystromformer = NystromformerModel(config)
        self.dropout = nn.Dropout(p=config.hidden_dropout_prob)
        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,
        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], TokenClassifierOutput]:
        r"""
        Args:
            labels (`mindspore.Tensor` 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.nystromformer(
            input_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[1:]
            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.nystromformer.modeling_nystromformer.NystromformerForTokenClassification.forward(input_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: `mindspore.Tensor` of shape `(batch_size, sequence_length)`, *optional* DEFAULT: None

Source code in mindnlp/transformers/models/nystromformer/modeling_nystromformer.py

def forward(
    self,
    input_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], TokenClassifierOutput]:
    r"""
    Args:
        labels (`mindspore.Tensor` 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.nystromformer(
        input_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[1:]
        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.nystromformer.modeling_nystromformer.NystromformerModel

Bases: NystromformerPreTrainedModel

Source code in mindnlp/transformers/models/nystromformer/modeling_nystromformer.py

class NystromformerModel(NystromformerPreTrainedModel):
    def __init__(self, config):
        super().__init__(config)
        self.config = config

        self.embeddings = NystromformerEmbeddings(config)
        self.encoder = NystromformerEncoder(config)

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

    def get_input_embeddings(self):
        return self.embeddings.word_embeddings

    def set_input_embeddings(self, value):
        self.embeddings.word_embeddings = value

    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,
        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,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
    ) -> Union[Tuple[mindspore.Tensor], BaseModelOutputWithPastAndCrossAttentions]:
        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 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

        if attention_mask is None:
            attention_mask = ops.ones(((batch_size, seq_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.expand(batch_size, seq_length)
                token_type_ids = buffered_token_type_ids_expanded
            else:
                token_type_ids = ops.zeros(input_shape, dtype=mstype.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)

        # 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,
            position_ids=position_ids,
            token_type_ids=token_type_ids,
            inputs_embeds=inputs_embeds,
        )
        encoder_outputs = self.encoder(
            embedding_output,
            attention_mask=extended_attention_mask,
            head_mask=head_mask,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )
        sequence_output = encoder_outputs[0]

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

        return BaseModelOutputWithPastAndCrossAttentions(
            last_hidden_state=sequence_output,
            hidden_states=encoder_outputs.hidden_states,
            attentions=encoder_outputs.attentions,
            cross_attentions=encoder_outputs.cross_attentions,
        )

mindnlp.transformers.models.nystromformer.modeling_nystromformer.NystromformerPreTrainedModel

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/nystromformer/modeling_nystromformer.py

class NystromformerPreTrainedModel(PreTrainedModel):
    """
    An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained
    models.
    """

    config_class = NystromformerConfig
    base_model_prefix = "nystromformer"
    supports_gradient_checkpointing = True

    def _init_weights(self, cell):
        """Initialize the weights"""
        if isinstance(cell, (nn.Linear, nn.Conv2d)):
            # 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(Tensor(weight, cell.weight.dtype))
        elif isinstance(cell, nn.LayerNorm):
            cell.weight.set_data(initializer('ones', cell.weight.shape, cell.weight.dtype))
            cell.bias.set_data(initializer('zeros', cell.bias.shape, cell.bias.dtype))