AutoAndroidController/py/venv/Lib/site-packages/modelscope/models/nlp/megatron_bert/backbone.py

# Copyright (c) Alibaba, Inc. and its affiliates.
# Copyright 2018 The Google AI Language Team Authors and The HuggingFace Inc. team.
# Copyright (c) 2018, NVIDIA CORPORATION.  All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
""" PyTorch MegatronBERT model."""

import math

import torch
import torch.utils.checkpoint
from torch import nn
from transformers.activations import ACT2FN
from transformers.modeling_utils import PreTrainedModel

from modelscope.metainfo import Models
from modelscope.models import Model, TorchModel
from modelscope.models.builder import MODELS
from modelscope.outputs import AttentionBackboneModelOutput
from modelscope.utils.constant import Tasks
from modelscope.utils.logger import get_logger
from modelscope.utils.nlp.utils import parse_labels_in_order
from modelscope.utils.torch_utils import (apply_chunking_to_forward,
                                          find_pruneable_heads_and_indices,
                                          prune_linear_layer)
from .configuration import MegatronBertConfig

logger = get_logger()

_CONFIG_FOR_DOC = 'MegatronBertConfig'


class MegatronBertEmbeddings(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,
                                                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

        # In Megatron, layer-norm is applied after the 1st dropout.
        # self.LayerNorm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
        self.dropout = nn.Dropout(config.hidden_dropout_prob)

        # position_ids (1, len position emb) is contiguous in memory and exported when serialized
        self.register_buffer(
            'position_ids',
            torch.arange(config.max_position_embeddings).expand((1, -1)))
        self.position_embedding_type = getattr(config,
                                               'position_embedding_type',
                                               'absolute')

    def forward(
        self,
        input_ids=None,
        token_type_ids=None,
        position_ids=None,
        inputs_embeds=None,
        past_key_values_length=0,
    ) -> torch.Tensor:
        if input_ids is not None:
            input_shape = input_ids.size()
        else:
            input_shape = inputs_embeds.size()[:-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]

        if token_type_ids is None:
            token_type_ids = torch.zeros(
                input_shape, dtype=torch.long, device=self.position_ids.device)

        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

        # Megatron BERT moves that layer norm after the drop-out (and to each layer).
        # embeddings = self.LayerNorm(embeddings)
        embeddings = self.dropout(embeddings)
        return embeddings


# Copied from transformers.models.bert.modeling_bert.BertSelfAttention with Bert->MegatronBert
class MegatronBertSelfAttention(nn.Module):

    def __init__(self, config, position_embedding_type=None):
        super().__init__()
        if config.hidden_size % config.num_attention_heads != 0 and not hasattr(
                config, 'embedding_size'):
            raise ValueError(
                f'The hidden size ({config.hidden_size}) is not a multiple of the number of attention '
                f'heads ({config.num_attention_heads})')

        self.num_attention_heads = config.num_attention_heads
        self.attention_head_size = int(config.hidden_size
                                       / config.num_attention_heads)
        self.all_head_size = self.num_attention_heads * self.attention_head_size

        self.query = nn.Linear(config.hidden_size, self.all_head_size)
        self.key = nn.Linear(config.hidden_size, self.all_head_size)
        self.value = nn.Linear(config.hidden_size, self.all_head_size)

        self.dropout = nn.Dropout(config.attention_probs_dropout_prob)
        self.position_embedding_type = position_embedding_type or getattr(
            config, 'position_embedding_type', 'absolute')
        if self.position_embedding_type == 'relative_key' or self.position_embedding_type == 'relative_key_query':
            self.max_position_embeddings = config.max_position_embeddings
            self.distance_embedding = nn.Embedding(
                2 * config.max_position_embeddings - 1,
                self.attention_head_size)

        self.is_decoder = config.is_decoder

    def transpose_for_scores(self, x: torch.Tensor) -> torch.Tensor:
        new_x_shape = x.size()[:-1] + (self.num_attention_heads,
                                       self.attention_head_size)
        x = x.view(new_x_shape)
        return x.permute(0, 2, 1, 3)

    def forward(
        self,
        hidden_states,
        attention_mask=None,
        head_mask=None,
        encoder_hidden_states=None,
        encoder_attention_mask=None,
        past_key_value=None,
        output_attentions=False,
    ):
        mixed_query_layer = self.query(hidden_states)

        # If this is instantiated as a cross-attention module, the keys
        # and values come from an encoder; the attention mask needs to be
        # such that the encoder's padding tokens are not attended to.
        is_cross_attention = encoder_hidden_states is not None

        if is_cross_attention and past_key_value is not None:
            # reuse k,v, cross_attentions
            key_layer = past_key_value[0]
            value_layer = past_key_value[1]
            attention_mask = encoder_attention_mask
        elif is_cross_attention:
            key_layer = self.transpose_for_scores(
                self.key(encoder_hidden_states))
            value_layer = self.transpose_for_scores(
                self.value(encoder_hidden_states))
            attention_mask = encoder_attention_mask
        elif past_key_value is not None:
            key_layer = self.transpose_for_scores(self.key(hidden_states))
            value_layer = self.transpose_for_scores(self.value(hidden_states))
            key_layer = torch.cat([past_key_value[0], key_layer], dim=2)
            value_layer = torch.cat([past_key_value[1], value_layer], dim=2)
        else:
            key_layer = self.transpose_for_scores(self.key(hidden_states))
            value_layer = self.transpose_for_scores(self.value(hidden_states))

        query_layer = self.transpose_for_scores(mixed_query_layer)

        if self.is_decoder:
            # if cross_attention save Tuple(torch.Tensor, torch.Tensor) of all cross attention key/value_states.
            # Further calls to cross_attention layer can then reuse all cross-attention
            # key/value_states (first "if" case)
            # if uni-directional self-attention (decoder) save Tuple(torch.Tensor, torch.Tensor) of
            # all previous decoder key/value_states. Further calls to uni-directional self-attention
            # can concat previous decoder key/value_states to current projected key/value_states (third "elif" case)
            # if encoder bi-directional self-attention `past_key_value` is always `None`
            past_key_value = (key_layer, value_layer)

        # Take the dot product between "query" and "key" to get the raw attention scores.
        attention_scores = torch.matmul(query_layer,
                                        key_layer.transpose(-1, -2))

        if self.position_embedding_type == 'relative_key' or self.position_embedding_type == 'relative_key_query':
            seq_length = hidden_states.size()[1]
            position_ids_l = torch.arange(
                seq_length, dtype=torch.long,
                device=hidden_states.device).view(-1, 1)
            position_ids_r = torch.arange(
                seq_length, dtype=torch.long,
                device=hidden_states.device).view(1, -1)
            distance = position_ids_l - position_ids_r
            positional_embedding = self.distance_embedding(
                distance + self.max_position_embeddings - 1)
            positional_embedding = positional_embedding.to(
                dtype=query_layer.dtype)  # fp16 compatibility

            if self.position_embedding_type == 'relative_key':
                relative_position_scores = torch.einsum(
                    'bhld,lrd->bhlr', query_layer, positional_embedding)
                attention_scores = attention_scores + relative_position_scores
            elif self.position_embedding_type == 'relative_key_query':
                relative_position_scores_query = torch.einsum(
                    'bhld,lrd->bhlr', query_layer, positional_embedding)
                relative_position_scores_key = torch.einsum(
                    'bhrd,lrd->bhlr', key_layer, positional_embedding)
                attention_scores = attention_scores + relative_position_scores_query + relative_position_scores_key

        attention_scores = attention_scores / math.sqrt(
            self.attention_head_size)
        if attention_mask is not None:
            # Apply the attention mask is (precomputed for all layers in MegatronBertModel forward() function)
            attention_scores = attention_scores + attention_mask

        # Normalize the attention scores to probabilities.
        attention_probs = nn.functional.softmax(attention_scores, dim=-1)

        # This is actually dropping out entire tokens to attend to, which might
        # seem a bit unusual, but is taken from the original Transformer paper.
        attention_probs = self.dropout(attention_probs)

        # Mask heads if we want to
        if head_mask is not None:
            attention_probs = attention_probs * head_mask

        context_layer = torch.matmul(attention_probs, value_layer)

        context_layer = context_layer.permute(0, 2, 1, 3).contiguous()
        new_context_layer_shape = context_layer.size()[:-2] + (
            self.all_head_size, )
        context_layer = context_layer.view(new_context_layer_shape)

        outputs = (context_layer,
                   attention_probs) if output_attentions else (context_layer, )

        if self.is_decoder:
            outputs = outputs + (past_key_value, )
        return outputs


# Based transformers.models.bert.modeling_bert.BertSelfOutput. Moved LayerNorm to MegatronBertAttention below.
class MegatronBertSelfOutput(nn.Module):

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

    def forward(self, hidden_states, residual):
        hidden_states = self.dense(hidden_states)
        hidden_states = self.dropout(hidden_states)
        return residual + hidden_states


# Based transformers.models.bert.modeling_bert.BertAttention. Added LayerNorm.
class MegatronBertAttention(nn.Module):

    def __init__(self, config):
        super().__init__()
        self.ln = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
        self.self = MegatronBertSelfAttention(config)
        self.output = MegatronBertSelfOutput(config)
        self.pruned_heads = set()

    def prune_heads(self, heads):
        if len(heads) == 0:
            return
        heads, index = find_pruneable_heads_and_indices(
            heads, self.self.num_attention_heads,
            self.self.attention_head_size, self.pruned_heads)

        # Prune linear layers
        self.self.query = prune_linear_layer(self.self.query, index)
        self.self.key = prune_linear_layer(self.self.key, index)
        self.self.value = prune_linear_layer(self.self.value, index)
        self.output.dense = prune_linear_layer(self.output.dense, index, dim=1)

        # Update hyper params and store pruned heads
        self.self.num_attention_heads = self.self.num_attention_heads - len(
            heads)
        self.self.all_head_size = self.self.attention_head_size * self.self.num_attention_heads
        self.pruned_heads = self.pruned_heads.union(heads)

    def forward(
        self,
        hidden_states,
        attention_mask=None,
        head_mask=None,
        encoder_hidden_states=None,
        encoder_attention_mask=None,
        past_key_value=None,
        output_attentions=False,
    ):
        ln_outputs = self.ln(hidden_states)
        self_outputs = self.self(
            ln_outputs,
            attention_mask,
            head_mask,
            encoder_hidden_states,
            encoder_attention_mask,
            past_key_value,
            output_attentions,
        )
        attention_output = self.output(self_outputs[0], hidden_states)
        outputs = (attention_output,
                   ) + self_outputs[1:]  # add attentions if we output them
        return outputs


# Copied from transformers.models.bert.modeling_bert.BertIntermediate with Bert->MegatronBert
class MegatronBertIntermediate(nn.Module):

    def __init__(self, config):
        super().__init__()
        self.dense = nn.Linear(config.hidden_size, config.intermediate_size)
        if isinstance(config.hidden_act, str):
            self.intermediate_act_fn = ACT2FN[config.hidden_act]
        else:
            self.intermediate_act_fn = config.hidden_act

    def forward(self, hidden_states):
        hidden_states = self.dense(hidden_states)
        hidden_states = self.intermediate_act_fn(hidden_states)
        return hidden_states


# Based on transformers.models.bert.modeling_bert.BertOutput. Moved LayerNorm to MegatronBertLayer below.
class MegatronBertOutput(nn.Module):

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

    def forward(self, hidden_states: torch.Tensor,
                input_tensor: torch.Tensor) -> torch.Tensor:
        hidden_states = self.dense(hidden_states)
        hidden_states = self.dropout(hidden_states)
        return input_tensor + hidden_states


# Based on transformers.models.bert.modeling_bert.BertLayer. Added LayerNorm.
class MegatronBertLayer(nn.Module):

    def __init__(self, config):
        super().__init__()
        self.chunk_size_feed_forward = config.chunk_size_feed_forward
        self.seq_len_dim = 1
        self.attention = MegatronBertAttention(config)
        self.is_decoder = config.is_decoder
        self.add_cross_attention = config.add_cross_attention
        if self.add_cross_attention:
            if not self.is_decoder:
                raise TypeError(
                    f'{self} should be used as a decoder model if cross attention is added'
                )
            self.crossattention = MegatronBertAttention(config)
        self.ln = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
        self.intermediate = MegatronBertIntermediate(config)
        self.output = MegatronBertOutput(config)

    def forward(
        self,
        hidden_states,
        attention_mask=None,
        head_mask=None,
        encoder_hidden_states=None,
        encoder_attention_mask=None,
        past_key_value=None,
        output_attentions=False,
    ):
        # decoder uni-directional self-attention cached key/values tuple is at positions 1,2
        self_attn_past_key_value = past_key_value[:
                                                  2] if past_key_value is not None else None
        self_attention_outputs = self.attention(
            hidden_states,
            attention_mask,
            head_mask,
            output_attentions=output_attentions,
            past_key_value=self_attn_past_key_value,
        )
        attention_output = self_attention_outputs[0]

        # if decoder, the last output is tuple of self-attn cache
        if self.is_decoder:
            outputs = self_attention_outputs[1:-1]
            present_key_value = self_attention_outputs[-1]
        else:
            outputs = self_attention_outputs[
                1:]  # add self attentions if we output attention weights

        cross_attn_present_key_value = None
        if self.is_decoder and encoder_hidden_states is not None:
            if not hasattr(self, 'crossattention'):
                raise AttributeError(
                    f'If `encoder_hidden_states` are passed, {self} has to be instantiated with cross-attention layers'
                    ' by setting `config.add_cross_attention=True`')

            # cross_attn cached key/values tuple is at positions 3,4 of past_key_value tuple
            cross_attn_past_key_value = past_key_value[
                -2:] if past_key_value is not None else None
            cross_attention_outputs = self.crossattention(
                attention_output,
                attention_mask,
                head_mask,
                encoder_hidden_states,
                encoder_attention_mask,
                cross_attn_past_key_value,
                output_attentions,
            )
            attention_output = cross_attention_outputs[0]
            outputs = outputs + cross_attention_outputs[
                1:-1]  # add cross attentions if we output attention weights

            # add cross-attn cache to positions 3,4 of present_key_value tuple
            cross_attn_present_key_value = cross_attention_outputs[-1]
            present_key_value = present_key_value + cross_attn_present_key_value

        layer_output = apply_chunking_to_forward(self.feed_forward_chunk,
                                                 self.chunk_size_feed_forward,
                                                 self.seq_len_dim,
                                                 attention_output)
        outputs = (layer_output, ) + outputs

        # if decoder, return the attn key/values as the last output
        if self.is_decoder:
            outputs = outputs + (present_key_value, )

        return outputs

    def feed_forward_chunk(self, attention_output):
        ln_output = self.ln(attention_output)
        intermediate_output = self.intermediate(ln_output)
        layer_output = self.output(intermediate_output, attention_output)
        return layer_output


class MegatronBertEncoder(nn.Module):

    def __init__(self, config):
        super().__init__()
        self.config = config
        self.layer = nn.ModuleList([
            MegatronBertLayer(config) for _ in range(config.num_hidden_layers)
        ])

        # The final layer norm. We removed the 1st LN, moved LN to each hidden layer and this one
        # is simply the final LN (Transformer's BERT has it attached to each hidden layer).
        self.ln = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
        self.gradient_checkpointing = False

    def forward(
        self,
        hidden_states,
        attention_mask=None,
        head_mask=None,
        encoder_hidden_states=None,
        encoder_attention_mask=None,
        past_key_values=None,
        use_cache=None,
        output_attentions=False,
        output_hidden_states=False,
        return_dict=True,
    ):
        all_hidden_states = () if output_hidden_states else None
        all_self_attentions = () if output_attentions else None
        all_cross_attentions = (
        ) if output_attentions and self.config.add_cross_attention else None

        next_decoder_cache = () if use_cache else None
        for i, layer_module in enumerate(self.layer):
            if output_hidden_states:
                all_hidden_states = all_hidden_states + (hidden_states, )

            layer_head_mask = head_mask[i] if head_mask is not None else None
            past_key_value = past_key_values[
                i] if past_key_values is not None else None

            if self.gradient_checkpointing and self.training:

                if use_cache:
                    logger.warning(
                        '`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...'
                    )
                    use_cache = False

                def create_custom_forward(module):

                    def custom_forward(*inputs):
                        return module(*inputs, past_key_value,
                                      output_attentions)

                    return custom_forward

                layer_outputs = torch.utils.checkpoint.checkpoint(
                    create_custom_forward(layer_module),
                    hidden_states,
                    attention_mask,
                    layer_head_mask,
                    encoder_hidden_states,
                    encoder_attention_mask,
                )
            else:
                layer_outputs = layer_module(
                    hidden_states,
                    attention_mask,
                    layer_head_mask,
                    encoder_hidden_states,
                    encoder_attention_mask,
                    past_key_value,
                    output_attentions,
                )

            # Because we moved the layer-norm at the end of the hidden layer, we have non-normali-
            # zed data here. If that's really needed, we must apply LN to match Transformer's BERT.

            hidden_states = layer_outputs[0]
            if use_cache:
                next_decoder_cache += (layer_outputs[-1], )
            if output_attentions:
                all_self_attentions = all_self_attentions + (
                    layer_outputs[1], )
                if self.config.add_cross_attention:
                    all_cross_attentions = all_cross_attentions + (
                        layer_outputs[2], )

        # Finalize the hidden states.
        hidden_states = self.ln(hidden_states)

        if output_hidden_states:
            all_hidden_states = all_hidden_states + (hidden_states, )

        if not return_dict:
            return tuple(v for v in [
                hidden_states,
                next_decoder_cache,
                all_hidden_states,
                all_self_attentions,
                all_cross_attentions,
            ] if v is not None)
        return AttentionBackboneModelOutput(
            last_hidden_state=hidden_states,
            past_key_values=next_decoder_cache,
            hidden_states=all_hidden_states,
            attentions=all_self_attentions,
            cross_attentions=all_cross_attentions,
        )


# Copied from transformers.models.bert.modeling_bert.BertPooler with Bert->MegatronBert
class MegatronBertPooler(nn.Module):

    def __init__(self, config):
        super().__init__()
        self.dense = nn.Linear(config.hidden_size, config.hidden_size)
        self.activation = nn.Tanh()

    def forward(self, hidden_states):
        # We "pool" the model by simply taking the hidden state corresponding
        # to the first token.
        first_token_tensor = hidden_states[:, 0]
        pooled_output = self.dense(first_token_tensor)
        pooled_output = self.activation(pooled_output)
        return pooled_output


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

    config_class = MegatronBertConfig
    base_model_prefix = 'bert'
    supports_gradient_checkpointing = True
    _keys_to_ignore_on_load_missing = [r'position_ids']

    def __init__(self, config, **kwargs):
        super().__init__(config.name_or_path, **kwargs)
        super(Model, self).__init__(config)

    def _init_weights(self, module):
        """Initialize the weights"""
        if isinstance(module, (nn.Linear, nn.Embedding)):
            # Slightly different from the TF version which uses truncated_normal for initialization
            # cf https://github.com/pytorch/pytorch/pull/5617
            module.weight.data.normal_(
                mean=0.0, std=self.config.initializer_range)
        elif isinstance(module, nn.LayerNorm):
            module.bias.data.zero_()
            module.weight.data.fill_(1.0)
        if isinstance(module, nn.Linear) and module.bias is not None:
            module.bias.data.zero_()

    def _set_gradient_checkpointing(self, module, value=False):
        if isinstance(module, MegatronBertEncoder):
            module.gradient_checkpointing = value

    @classmethod
    def _instantiate(cls, **kwargs):
        """Instantiate the model.

        Args:
            kwargs: Input args.
                    model_dir: The model dir used to load the checkpoint and the label information.
                    num_labels: An optional arg to tell the model how many classes to initialize.
                                    Method will call utils.parse_label_mapping if num_labels not supplied.
                                    If num_labels is not found, the model will use the default setting (2 classes).

        Returns:
            The loaded model, which is initialized by transformers.PreTrainedModel.from_pretrained
        """

        model_dir = kwargs.pop('model_dir', None)
        cfg = kwargs.pop('cfg', None)
        model_args = parse_labels_in_order(model_dir, cfg, **kwargs)
        if model_dir is None:
            config = MegatronBertConfig(**model_args)
            model = cls(config)
        else:
            model = super(Model, cls).from_pretrained(
                pretrained_model_name_or_path=model_dir, **model_args)
        model.model_dir = model_dir
        return model


@MODELS.register_module(
    group_key=Tasks.backbone, module_name=Models.megatron_bert)
class MegatronBertModel(MegatronBertPreTrainedModel):
    """The bare MegatronBert Model transformer outputting raw hidden-states without any specific head on top.",

    This model inherits from [`PreTrainedModel`]. Check the superclass documentation for the generic methods the
    library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads
    etc.)

    This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass.
    Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage
    and behavior.

    Parameters:
        config ([`MegatronBertConfig`]): Model configuration class with all the parameters of the model.
            Initializing with a config file does not load the weights associated with the model, only the
            configuration. Check out the [`~PreTrainedModel.from_pretrained`] method to load the model weights.

    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 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.
    """

    def __init__(self, config, add_pooling_layer=True):
        super().__init__(config)
        self.config = config

        self.embeddings = MegatronBertEmbeddings(config)
        self.encoder = MegatronBertEncoder(config)

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

        # 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=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,
                **kwargs) -> AttentionBackboneModelOutput:
        r"""
        Args:
            input_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`):
                Indices of input sequence tokens in the vocabulary.

                Indices can be obtained using [`BertTokenizer`]. See
                [`PreTrainedTokenizer.encode`] and [`PreTrainedTokenizer.__call__`]
                for details.

                [What are input IDs?](../glossary#input-ids)
            attention_mask (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*):
                Mask to avoid performing attention on padding token indices. Mask
                values selected in `[0, 1]`:

                - 1 for tokens that are **not masked**,
                - 0 for tokens that are **masked**.

                [What are attention masks?](../glossary#attention-mask)
            token_type_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
                Segment token indices to indicate first and second portions of the
                inputs. Indices are selected in `[0, 1]`:

                - 0 corresponds to a *sentence A* token,
                - 1 corresponds to a *sentence B* token.

                [What are token type IDs?](../glossary#token-type-ids)
            position_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
                Indices of positions of each input sequence tokens in the position
                embeddings. Selected in the range `[0,
                config.max_position_embeddings - 1]`.

                [What are position IDs?](../glossary#position-ids)
            head_mask (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers,
                num_heads)`, *optional*):
                Mask to nullify selected heads of the self-attention modules. Mask
                values selected in `[0, 1]`:

                - 1 indicates the head is **not masked**,
                - 0 indicates the head is **masked**.

            inputs_embeds (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`,
                *optional*):
                Optionally, instead of passing `input_ids` you can choose to
                directly pass an embedded representation. This is useful if you want
                more control over how to convert `input_ids` indices into associated
                vectors than the model's internal embedding lookup matrix.
            output_attentions (`bool`, *optional*):
                Whether or not to return the attentions tensors of all attention
                layers. See `attentions` under returned tensors for more detail.
            output_hidden_states (`bool`, *optional*):
                Whether or not to return the hidden states of all layers. See
                `hidden_states` under returned tensors for more detail.
            return_dict (`bool`, *optional*):
                Whether or not to return a [`~file_utils.ModelOutput`] instead of a
                plain tuple.
            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`).
            Others (**kwargs)
                some additional parameters might passed in from upstream pipeline,
                which not influence the results.
        """
        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:
            input_shape = input_ids.size()
        elif inputs_embeds is not None:
            input_shape = inputs_embeds.size()[:-1]
        else:
            raise ValueError(
                'You have to specify either input_ids or inputs_embeds')

        batch_size, seq_length = input_shape
        device = input_ids.device if input_ids is not None else inputs_embeds.device

        # 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 = torch.ones(
                ((batch_size, seq_length + past_key_values_length)),
                device=device)
        if token_type_ids is None:
            token_type_ids = torch.zeros(
                input_shape, dtype=torch.long, device=device)

        # 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: torch.Tensor = self.get_extended_attention_mask(
            attention_mask, input_shape, device)

        # 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.size(
            )
            encoder_hidden_shape = (encoder_batch_size,
                                    encoder_sequence_length)
            if encoder_attention_mask is None:
                encoder_attention_mask = torch.ones(
                    encoder_hidden_shape, device=device)
            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,
            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 AttentionBackboneModelOutput(
            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,
        )