ColossalAI/colossalai/shardformer/modeling/bert.py

import math
import warnings
from typing import Dict, List, Optional, Tuple, Union

import torch
from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss
from transformers.modeling_outputs import (
    BaseModelOutputWithPoolingAndCrossAttentions,
    CausalLMOutputWithCrossAttentions,
    MaskedLMOutput,
    MultipleChoiceModelOutput,
    NextSentencePredictorOutput,
    QuestionAnsweringModelOutput,
    SequenceClassifierOutput,
    TokenClassifierOutput,
)
from transformers.models.bert.modeling_bert import (
    BertForMaskedLM,
    BertForMultipleChoice,
    BertForNextSentencePrediction,
    BertForPreTraining,
    BertForPreTrainingOutput,
    BertForQuestionAnswering,
    BertForSequenceClassification,
    BertForTokenClassification,
    BertLMHeadModel,
    BertModel,
)
from transformers.utils import logging

from colossalai.pipeline.stage_manager import PipelineStageManager
from colossalai.shardformer import ShardConfig
from colossalai.shardformer.layer._operation import gather_forward_split_backward, split_forward_gather_backward


class BertPipelineForwards:
    '''
    This class serves as a micro library for forward function substitution of Bert models
    under pipeline setting.
    '''

    @staticmethod
    def bert_model_forward(
        self: BertModel,
        input_ids: Optional[torch.Tensor] = None,
        attention_mask: Optional[torch.Tensor] = None,
        token_type_ids: Optional[torch.Tensor] = None,
        position_ids: Optional[torch.Tensor] = None,
        head_mask: Optional[torch.Tensor] = None,
        inputs_embeds: Optional[torch.Tensor] = None,
        encoder_hidden_states: Optional[torch.Tensor] = None,
        encoder_attention_mask: Optional[torch.Tensor] = None,
        past_key_values: Optional[List[torch.FloatTensor]] = None,
        use_cache: Optional[bool] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
        stage_manager: Optional[PipelineStageManager] = None,
        hidden_states: Optional[torch.FloatTensor] = None,    # this is from the previous stage
        stage_index: Optional[List[int]] = None,
        shard_config: ShardConfig = None,
    ):
        # TODO(jianghai): add explaination of the output here.
        r"""
            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`).
            """
        logger = logging.get_logger(__name__)

        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 stage_manager.is_first_stage():
            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
            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 = torch.zeros(input_shape, dtype=torch.long, device=device)
        else:
            input_shape = hidden_states.size()[:-1]
            batch_size, seq_length = input_shape
            device = hidden_states.device

        # TODO(jianghai): left the recording kv-value tensors as () or None type, this feature may be added in the future.
        if output_attentions:
            logger.warning_once('output_attentions=True is not supported for pipeline models at the moment.')
            output_attentions = False
        if output_hidden_states:
            logger.warning_once('output_hidden_states=True is not supported for pipeline models at the moment.')
            output_hidden_states = False
        if use_cache:
            logger.warning_once('use_cache=True is not supported for pipeline models at the moment.')
            use_cache = False

        # 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)

        # 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)
        attention_mask = extended_attention_mask
        # 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)
        hidden_states = hidden_states if hidden_states is not None else None

        if stage_manager.is_first_stage():
            hidden_states = 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,
            )

        # inherit from bert_layer,this should be changed when we add the feature to record hidden_states
        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

        if self.encoder.gradient_checkpointing and self.encoder.training:
            if use_cache:
                logger.warning_once(
                    "`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...")
                use_cache = False
        next_decoder_cache = () if use_cache else None

        start_idx, end_idx = stage_index[0], stage_index[1]
        # layer_outputs
        layer_outputs = hidden_states if hidden_states is not None else None

        # split the input tensor along sequence dimension
        # [batch_size, seq_len, hidden_size] -> [batch_size, seq_len/TP_size, hidden_size]
        if shard_config is not None and shard_config.enable_sequence_parallelism:
            hidden_states = split_forward_gather_backward(hidden_states,
                                                          dim=1,
                                                          process_group=shard_config.tensor_parallel_process_group)
            if encoder_hidden_states is not None:
                encoder_hidden_states = split_forward_gather_backward(
                    encoder_hidden_states, dim=1, process_group=shard_config.tensor_parallel_process_group)

        for idx, encoder_layer in enumerate(self.encoder.layer[start_idx:end_idx], start=start_idx):
            if stage_manager.is_first_stage() and idx == 0:
                encoder_attention_mask = encoder_extended_attention_mask

            if output_hidden_states:
                all_hidden_states = all_hidden_states + (hidden_states,)

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

            if self.encoder.gradient_checkpointing and self.encoder.training:

                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(encoder_layer),
                    hidden_states,
                    attention_mask,
                    layer_head_mask,
                    encoder_hidden_states,
                    encoder_attention_mask,
                )
            else:
                layer_outputs = encoder_layer(
                    hidden_states,
                    attention_mask,
                    layer_head_mask,
                    encoder_hidden_states,
                    encoder_attention_mask,
                    past_key_value,
                    output_attentions,
                )
            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],)

        # When sequence parallelism done, gather the output tensor in forward and split it in backward
        if shard_config is not None and shard_config.enable_sequence_parallelism:
            hidden_states = gather_forward_split_backward(hidden_states,
                                                          dim=1,
                                                          process_group=shard_config.tensor_parallel_process_group)

        if output_hidden_states:
            all_hidden_states = all_hidden_states + (hidden_states,)

        # end of a stage loop
        sequence_output = hidden_states if hidden_states is not None else None

        if stage_manager.is_last_stage():
            pooled_output = self.pooler(sequence_output) if self.pooler is not None else None
            if not return_dict:
                return (sequence_output, pooled_output) + layer_outputs[1:]
            # return dict is not supported at this moment
            else:
                return BaseModelOutputWithPoolingAndCrossAttentions(
                    last_hidden_state=sequence_output,
                    pooler_output=pooled_output,
                    past_key_values=next_decoder_cache,
                    hidden_states=all_hidden_states,
                    attentions=all_self_attentions,
                    cross_attentions=all_cross_attentions,
                )

        # output of non-first and non-last stages: must be a dict
        else:
            # intermediate stage always return dict
            return {
                'hidden_states': hidden_states,
            }

    @staticmethod
    def bert_for_pretraining_forward(
        self: BertForPreTraining,
        input_ids: Optional[torch.Tensor] = None,
        attention_mask: Optional[torch.Tensor] = None,
        token_type_ids: Optional[torch.Tensor] = None,
        position_ids: Optional[torch.Tensor] = None,
        head_mask: Optional[torch.Tensor] = None,
        inputs_embeds: Optional[torch.Tensor] = None,
        labels: Optional[torch.Tensor] = None,
        next_sentence_label: Optional[torch.Tensor] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
        hidden_states: Optional[torch.FloatTensor] = None,
        stage_manager: Optional[PipelineStageManager] = None,
        stage_index: Optional[List[int]] = None,
        shard_config: ShardConfig = None,
    ):
        logger = logging.get_logger(__name__)

        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
        # TODO(jianghai) left the recording kv-value tensors as () or None type, this feature may be added in the future.
        if output_attentions:
            logger.warning_once('output_attentions=True is not supported for pipeline models at the moment.')
            output_attentions = False
        if output_hidden_states:
            logger.warning_once('output_hidden_states=True is not supported for pipeline models at the moment.')
            output_hidden_states = False

        outputs = BertPipelineForwards.bert_model_forward(
            self.bert,
            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,
            stage_manager=stage_manager,
            hidden_states=hidden_states if hidden_states is not None else None,
            stage_index=stage_index,
            shard_config=shard_config,
        )
        past_key_values = None
        all_hidden_states = None
        all_self_attentions = None
        all_cross_attentions = None

        if stage_manager.is_last_stage():
            sequence_output, pooled_output = outputs[:2]
            prediction_scores, seq_relationship_score = self.cls(sequence_output, pooled_output)
            # the last stage for pretraining model
            total_loss = None
            if labels is not None and next_sentence_label is not None:
                loss_fct = CrossEntropyLoss()
                masked_lm_loss = loss_fct(prediction_scores.view(-1, self.config.vocab_size), labels.view(-1))
                next_sentence_loss = loss_fct(seq_relationship_score.view(-1, 2), next_sentence_label.view(-1))
                total_loss = masked_lm_loss + next_sentence_loss

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

            return BertForPreTrainingOutput(
                loss=total_loss,
                prediction_logits=prediction_scores,
                seq_relationship_logits=seq_relationship_score,
                hidden_states=outputs.hidden_states,
                attentions=outputs.attentions,
            )
        else:
            hidden_states = outputs.get('hidden_states')

            # intermediate stage always return dict
            return {
                'hidden_states': hidden_states,
            }

    @staticmethod
    def bert_lm_head_model_forward(
        self: BertLMHeadModel,
        input_ids: Optional[torch.Tensor] = None,
        attention_mask: Optional[torch.Tensor] = None,
        token_type_ids: Optional[torch.Tensor] = None,
        position_ids: Optional[torch.Tensor] = None,
        head_mask: Optional[torch.Tensor] = None,
        inputs_embeds: Optional[torch.Tensor] = None,
        encoder_hidden_states: Optional[torch.Tensor] = None,
        encoder_attention_mask: Optional[torch.Tensor] = None,
        labels: Optional[torch.Tensor] = None,
        past_key_values: Optional[List[torch.Tensor]] = None,
        use_cache: Optional[bool] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
        hidden_states: Optional[torch.FloatTensor] = None,
        stage_manager: Optional[PipelineStageManager] = None,
        stage_index: Optional[List[int]] = None,
        shard_config: ShardConfig = None,
    ):
        r"""
            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**.
            labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
                Labels for computing the left-to-right language modeling loss (next word prediction). Indices should be in
                `[-100, 0, ..., config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are
                ignored (masked), the loss is only computed for the tokens with labels n `[0, ..., config.vocab_size]`
            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`).
            """
        logger = logging.get_logger(__name__)
        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        if labels is not None:
            use_cache = False
        if output_attentions:
            logger.warning_once('output_attentions=True is not supported for pipeline models at the moment.')
            output_attentions = False
        if output_hidden_states:
            logger.warning_once('output_hidden_states=True is not supported for pipeline models at the moment.')
            output_hidden_states = False

        outputs = BertPipelineForwards.bert_model_forward(
            self.bert,
            input_ids,
            attention_mask=attention_mask,
            token_type_ids=token_type_ids,
            position_ids=position_ids,
            head_mask=head_mask,
            inputs_embeds=inputs_embeds,
            encoder_hidden_states=encoder_hidden_states,
            encoder_attention_mask=encoder_attention_mask,
            past_key_values=past_key_values,
            use_cache=use_cache,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
            stage_manager=stage_manager,
            hidden_states=hidden_states if hidden_states is not None else None,
            stage_index=stage_index,
            shard_config=shard_config)
        past_key_values = None
        all_hidden_states = None
        all_self_attentions = None
        all_cross_attentions = None

        if stage_manager.is_last_stage():
            sequence_output = outputs[0]
            prediction_scores = self.cls(sequence_output)

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

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

            return CausalLMOutputWithCrossAttentions(
                loss=lm_loss,
                logits=prediction_scores,
                past_key_values=outputs.past_key_values,
                hidden_states=outputs.hidden_states,
                attentions=outputs.attentions,
                cross_attentions=outputs.cross_attentions,
            )
        else:
            hidden_states = outputs.get('hidden_states')
            # intermediate stage always return dict
            return {'hidden_states': hidden_states}

    @staticmethod
    def bert_for_masked_lm_forward(
        self: BertForMaskedLM,
        input_ids: Optional[torch.Tensor] = None,
        attention_mask: Optional[torch.Tensor] = None,
        token_type_ids: Optional[torch.Tensor] = None,
        position_ids: Optional[torch.Tensor] = None,
        head_mask: Optional[torch.Tensor] = None,
        inputs_embeds: Optional[torch.Tensor] = None,
        encoder_hidden_states: Optional[torch.Tensor] = None,
        encoder_attention_mask: Optional[torch.Tensor] = None,
        labels: Optional[torch.Tensor] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
        hidden_states: Optional[torch.Tensor] = None,
        stage_manager: Optional[PipelineStageManager] = None,
        stage_index: Optional[List[int]] = None,
        shard_config: ShardConfig = None,
    ):
        r"""
            labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
                Labels for computing the masked language modeling loss. Indices should be in `[-100, 0, ...,
                config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are ignored (masked), the
                loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`
            """
        logger = logging.get_logger(__name__)

        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        if output_attentions:
            logger.warning_once('output_attentions=True is not supported for pipeline models at the moment.')
            output_attentions = False
        if output_hidden_states:
            logger.warning_once('output_hidden_states=True is not supported for pipeline models at the moment.')
            output_hidden_states = False

        outputs = BertPipelineForwards.bert_model_forward(
            self.bert,
            input_ids,
            attention_mask=attention_mask,
            token_type_ids=token_type_ids,
            position_ids=position_ids,
            head_mask=head_mask,
            inputs_embeds=inputs_embeds,
            encoder_hidden_states=encoder_hidden_states,
            encoder_attention_mask=encoder_attention_mask,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
            hidden_states=hidden_states,
            stage_manager=stage_manager,
            stage_index=stage_index,
            shard_config=shard_config,
        )

        if stage_manager.is_last_stage():
            sequence_output = outputs[0]
            prediction_scores = self.cls(sequence_output)

            masked_lm_loss = None
            if labels is not None:
                loss_fct = CrossEntropyLoss()    # -100 index = padding token
                masked_lm_loss = loss_fct(prediction_scores.view(-1, self.config.vocab_size), labels.view(-1))

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

            return MaskedLMOutput(
                loss=masked_lm_loss,
                logits=prediction_scores,
                hidden_states=outputs.hidden_states,
                attentions=outputs.attentions,
            )
        else:
            hidden_states = outputs.get('hidden_states')
            return {'hidden_states': hidden_states}

    @staticmethod
    def bert_for_next_sentence_prediction_forward(
        self: BertForNextSentencePrediction,
        input_ids: Optional[torch.Tensor] = None,
        attention_mask: Optional[torch.Tensor] = None,
        token_type_ids: Optional[torch.Tensor] = None,
        position_ids: Optional[torch.Tensor] = None,
        head_mask: Optional[torch.Tensor] = None,
        inputs_embeds: Optional[torch.Tensor] = None,
        labels: Optional[torch.Tensor] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
        hidden_states: Optional[torch.Tensor] = None,
        stage_manager: Optional[PipelineStageManager] = None,
        stage_index: Optional[List[int]] = None,
        shard_config: ShardConfig = None,
        **kwargs,
    ):
        # -> Union[Tuple[torch.Tensor], NextSentencePredictorOutput]:
        r"""
            labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
                Labels for computing the next sequence prediction (classification) loss. Input should be a sequence pair
                (see `input_ids` docstring). Indices should be in `[0, 1]`:

                - 0 indicates sequence B is a continuation of sequence A,
                - 1 indicates sequence B is a random sequence.

            Returns:

            Example:

            ```python
            >>> from transformers import AutoTokenizer, BertForNextSentencePrediction
            >>> import torch

            >>> tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
            >>> model = BertForNextSentencePrediction.from_pretrained("bert-base-uncased")

            >>> prompt = "In Italy, pizza served in formal settings, such as at a restaurant, is presented unsliced."
            >>> next_sentence = "The sky is blue due to the shorter wavelength of blue light."
            >>> encoding = tokenizer(prompt, next_sentence, return_tensors="pt")

            >>> outputs = model(**encoding, labels=torch.LongTensor([1]))
            >>> logits = outputs.logits
            >>> assert logits[0, 0] < logits[0, 1]  # next sentence was random
            ```
            """
        logger = logging.get_logger(__name__)

        if "next_sentence_label" in kwargs:
            warnings.warn(
                "The `next_sentence_label` argument is deprecated and will be removed in a future version, use"
                " `labels` instead.",
                FutureWarning,
            )
            labels = kwargs.pop("next_sentence_label")

        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        if output_attentions:
            logger.warning_once('output_attentions=True is not supported for pipeline models at the moment.')
            output_attentions = False
        if output_hidden_states:
            logger.warning_once('output_hidden_states=True is not supported for pipeline models at the moment.')
            output_hidden_states = False

        outputs = BertPipelineForwards.bert_model_forward(self.bert,
                                                          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_states=hidden_states,
                                                          stage_manager=stage_manager,
                                                          stage_index=stage_index,
                                                          shard_config=shard_config)

        if stage_manager.is_last_stage():
            pooled_output = outputs[1]
            seq_relationship_scores = self.cls(pooled_output)

            next_sentence_loss = None
            if labels is not None:
                loss_fct = CrossEntropyLoss()
                next_sentence_loss = loss_fct(seq_relationship_scores.view(-1, 2), labels.view(-1))

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

            return NextSentencePredictorOutput(
                loss=next_sentence_loss,
                logits=seq_relationship_scores,
                hidden_states=outputs.hidden_states,
                attentions=outputs.attentions,
            )
        else:
            hidden_states = outputs.get('hidden_states')
            # intermediate stage always return dict
            return {'hidden_states': hidden_states}

    @staticmethod
    def bert_for_sequence_classification_forward(
        self: BertForSequenceClassification,
        input_ids: Optional[torch.Tensor] = None,
        attention_mask: Optional[torch.Tensor] = None,
        token_type_ids: Optional[torch.Tensor] = None,
        position_ids: Optional[torch.Tensor] = None,
        head_mask: Optional[torch.Tensor] = None,
        inputs_embeds: Optional[torch.Tensor] = None,
        labels: Optional[torch.Tensor] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
        hidden_states: Optional[torch.Tensor] = None,
        stage_manager: Optional[PipelineStageManager] = None,
        stage_index: Optional[List[int]] = None,
        shard_config: ShardConfig = None,
    ):
        r"""
        labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
            Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
            config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
            `config.num_labels > 1` a classification loss is computed (Cross-Entropy).
        """
        logger = logging.get_logger(__name__)

        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        if output_attentions:
            logger.warning_once('output_attentions=True is not supported for pipeline models at the moment.')
            output_attentions = False
        if output_hidden_states:
            logger.warning_once('output_hidden_states=True is not supported for pipeline models at the moment.')
            output_hidden_states = False

        outputs = BertPipelineForwards.bert_model_forward(self.bert,
                                                          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_states=hidden_states,
                                                          stage_manager=stage_manager,
                                                          stage_index=stage_index,
                                                          shard_config=shard_config)

        if stage_manager.is_last_stage():
            pooled_output = outputs[1]

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

            loss = None
            if labels is not None:
                if self.config.problem_type is None:
                    if self.num_labels == 1:
                        self.config.problem_type = "regression"
                    elif self.num_labels > 1 and (labels.dtype == torch.long or labels.dtype == torch.int):
                        self.config.problem_type = "single_label_classification"
                    else:
                        self.config.problem_type = "multi_label_classification"

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

            return SequenceClassifierOutput(
                loss=loss,
                logits=logits,
                hidden_states=outputs.hidden_states,
                attentions=outputs.attentions,
            )
        else:
            hidden_states = outputs.get('hidden_states')
            return {'hidden_states': hidden_states}

    @staticmethod
    def bert_for_token_classification_forward(
        self: BertForTokenClassification,
        input_ids: Optional[torch.Tensor] = None,
        attention_mask: Optional[torch.Tensor] = None,
        token_type_ids: Optional[torch.Tensor] = None,
        position_ids: Optional[torch.Tensor] = None,
        head_mask: Optional[torch.Tensor] = None,
        inputs_embeds: Optional[torch.Tensor] = None,
        labels: Optional[torch.Tensor] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
        hidden_states: Optional[torch.Tensor] = None,
        stage_manager: Optional[PipelineStageManager] = None,
        stage_index: Optional[List[int]] = None,
        shard_config: ShardConfig = None,
    ):
        r"""
        labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
            Labels for computing the token classification loss. Indices should be in `[0, ..., config.num_labels - 1]`.
        """
        logger = logging.get_logger(__name__)

        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        if output_attentions:
            logger.warning_once('output_attentions=True is not supported for pipeline models at the moment.')
            output_attentions = False
        if output_hidden_states:
            logger.warning_once('output_hidden_states=True is not supported for pipeline models at the moment.')
            output_hidden_states = False

        outputs = BertPipelineForwards.bert_model_forward(self.bert,
                                                          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_states=hidden_states,
                                                          stage_manager=stage_manager,
                                                          stage_index=stage_index,
                                                          shard_config=shard_config)

        if stage_manager.is_last_stage():
            sequence_output = outputs[0]

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

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

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

            return TokenClassifierOutput(
                loss=loss,
                logits=logits,
                hidden_states=outputs.hidden_states,
                attentions=outputs.attentions,
            )
        else:
            hidden_states = outputs.get('hidden_states')
            return {'hidden_states': hidden_states}

    @staticmethod
    def bert_for_multiple_choice_forward(
        self: BertForMultipleChoice,
        input_ids: Optional[torch.Tensor] = None,
        attention_mask: Optional[torch.Tensor] = None,
        token_type_ids: Optional[torch.Tensor] = None,
        position_ids: Optional[torch.Tensor] = None,
        head_mask: Optional[torch.Tensor] = None,
        inputs_embeds: Optional[torch.Tensor] = None,
        labels: Optional[torch.Tensor] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
        hidden_states: Optional[torch.Tensor] = None,
        stage_manager: Optional[PipelineStageManager] = None,
        stage_index: Optional[List[int]] = None,
        shard_config: ShardConfig = None,
    ):
        r"""
        labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
            Labels for computing the multiple choice classification loss. Indices should be in `[0, ...,
            num_choices-1]` where `num_choices` is the size of the second dimension of the input tensors. (See
            `input_ids` above)
        """
        logger = logging.get_logger(__name__)

        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        if output_attentions:
            logger.warning_once('output_attentions=True is not supported for pipeline models at the moment.')
            output_attentions = False
        if output_hidden_states:
            logger.warning_once('output_hidden_states=True is not supported for pipeline models at the moment.')
            output_hidden_states = False

        # in our pipeline design,input ids are copied for every stage and shouldn't be none
        # the input_ids for multiple choice model is [batch_size, num_choices, sequence_length]
        if stage_manager.is_last_stage():
            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.size(-1)) if input_ids is not None else None
        attention_mask = attention_mask.view(-1, attention_mask.size(-1)) if attention_mask is not None else None
        token_type_ids = token_type_ids.view(-1, token_type_ids.size(-1)) if token_type_ids is not None else None
        position_ids = position_ids.view(-1, position_ids.size(-1)) if position_ids is not None else None
        inputs_embeds = (inputs_embeds.view(-1, inputs_embeds.size(-2), inputs_embeds.size(-1))
                         if inputs_embeds is not None else None)

        outputs = BertPipelineForwards.bert_model_forward(
            self.bert,
            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_states=hidden_states,
            stage_manager=stage_manager,
            stage_index=stage_index,
            shard_config=shard_config,
        )
        if stage_manager.is_last_stage():
            pooled_output = outputs[1]
            pooled_output = self.dropout(pooled_output)
            logits = self.classifier(pooled_output)
            reshaped_logits = logits.view(-1, num_choices)

            loss = None
            if labels is not None:
                loss_fct = CrossEntropyLoss()
                loss = loss_fct(reshaped_logits, labels)

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

            return MultipleChoiceModelOutput(
                loss=loss,
                logits=reshaped_logits,
                hidden_states=outputs.hidden_states,
                attentions=outputs.attentions,
            )
        else:
            hidden_states = outputs.get('hidden_states')
            return {'hidden_states': hidden_states}

    @staticmethod
    def bert_for_question_answering_forward(
        self: BertForQuestionAnswering,
        input_ids: Optional[torch.Tensor] = None,
        attention_mask: Optional[torch.Tensor] = None,
        token_type_ids: Optional[torch.Tensor] = None,
        position_ids: Optional[torch.Tensor] = None,
        head_mask: Optional[torch.Tensor] = None,
        inputs_embeds: Optional[torch.Tensor] = None,
        start_positions: Optional[torch.Tensor] = None,
        end_positions: Optional[torch.Tensor] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
        hidden_states: Optional[torch.Tensor] = None,
        stage_manager: Optional[PipelineStageManager] = None,
        stage_index: Optional[List[int]] = None,
        shard_config: ShardConfig = None,
    ):
        # NOTE: the arg start_position and end_position are used only for the last stage
        r"""
        start_positions (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
            Labels for position (index) of the start of the labelled span for computing the token classification loss.
            Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence
            are not taken into account for computing the loss.
        end_positions (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
            Labels for position (index) of the end of the labelled span for computing the token classification loss.
            Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence
            are not taken into account for computing the loss.
        """
        logger = logging.get_logger(__name__)

        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        if output_attentions:
            logger.warning_once('output_attentions=True is not supported for pipeline models at the moment.')
            output_attentions = False
        if output_hidden_states:
            logger.warning_once('output_hidden_states=True is not supported for pipeline models at the moment.')
            output_hidden_states = False

        outputs = BertPipelineForwards.bert_model_forward(self.bert,
                                                          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_states=hidden_states,
                                                          stage_manager=stage_manager,
                                                          stage_index=stage_index,
                                                          shard_config=shard_config)
        if stage_manager.is_last_stage():
            sequence_output = outputs[0]

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

            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.size()) > 1:
                    start_positions = start_positions.squeeze(-1)
                if len(end_positions.size()) > 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.size(1)
                start_positions = start_positions.clamp(0, ignored_index)
                end_positions = end_positions.clamp(0, ignored_index)

                loss_fct = CrossEntropyLoss(ignore_index=ignored_index)
                start_loss = loss_fct(start_logits, start_positions)
                end_loss = loss_fct(end_logits, end_positions)
                total_loss = (start_loss + end_loss) / 2

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

            return QuestionAnsweringModelOutput(
                loss=total_loss,
                start_logits=start_logits,
                end_logits=end_logits,
                hidden_states=outputs.hidden_states,
                attentions=outputs.attentions,
            )
        else:
            hidden_states = outputs.get('hidden_states')
            return {'hidden_states': hidden_states}


def get_bert_flash_attention_forward():

    try:
        from xformers.ops import memory_efficient_attention as me_attention
    except:
        raise ImportError("Error: xformers module is not installed. Please install it to use flash attention.")
    from transformers.models.bert.modeling_bert import BertAttention

    def forward(
        self: BertAttention,
        hidden_states: torch.Tensor,
        attention_mask: Optional[torch.FloatTensor] = None,
        head_mask: Optional[torch.FloatTensor] = None,
        encoder_hidden_states: Optional[torch.FloatTensor] = None,
        encoder_attention_mask: Optional[torch.FloatTensor] = None,
        past_key_value: Optional[Tuple[Tuple[torch.FloatTensor]]] = None,
        output_attentions: Optional[bool] = False,
    ) -> Tuple[torch.Tensor]:
        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)

        use_cache = past_key_value is not None
        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)

        final_attention_mask = None
        if self.position_embedding_type == "relative_key" or self.position_embedding_type == "relative_key_query":
            query_length, key_length = query_layer.shape[2], key_layer.shape[2]
            if use_cache:
                position_ids_l = torch.tensor(key_length - 1, dtype=torch.long, device=hidden_states.device).view(-1, 1)
            else:
                position_ids_l = torch.arange(query_length, dtype=torch.long, device=hidden_states.device).view(-1, 1)
            position_ids_r = torch.arange(key_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)
                final_attention_mask = 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)
                final_attention_mask = relative_position_scores_query + relative_position_scores_key

        scale = 1 / math.sqrt(self.attention_head_size)
        if attention_mask is not None:
            if final_attention_mask != None:
                final_attention_mask = final_attention_mask * scale + attention_mask
            else:
                final_attention_mask = attention_mask

        if final_attention_mask is not None:
            batch_size, src_len = query_layer.size()[0], query_layer.size()[2]
            tgt_len = key_layer.size()[2]
            final_attention_mask = final_attention_mask.expand(batch_size, self.num_attention_heads, src_len,
                                                               tgt_len).contiguous()

        query_layer = query_layer.permute(0, 2, 1, 3).contiguous()
        key_layer = key_layer.permute(0, 2, 1, 3).contiguous()
        value_layer = value_layer.permute(0, 2, 1, 3).contiguous()

        context_layer = me_attention(query_layer,
                                     key_layer,
                                     value_layer,
                                     attn_bias=final_attention_mask,
                                     p=self.dropout.p,
                                     scale=scale)
        new_context_layer_shape = context_layer.size()[:-2] + (self.all_head_size,)
        context_layer = context_layer.view(new_context_layer_shape)

        outputs = (context_layer, None)

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

    return forward


def get_jit_fused_bert_self_output_forward():

    from transformers.models.bert.modeling_bert import BertSelfOutput

    def forward(self: BertSelfOutput, hidden_states: torch.Tensor, input_tensor: torch.Tensor) -> torch.Tensor:
        hidden_states = self.dense(hidden_states)
        hidden_states = self.dropout_add(hidden_states, input_tensor, self.dropout.p, self.dropout.training)
        hidden_states = self.LayerNorm(hidden_states)
        return hidden_states

    return forward


def get_jit_fused_bert_output_forward():

    from transformers.models.bert.modeling_bert import BertOutput

    def forward(self: BertOutput, hidden_states: torch.Tensor, input_tensor: torch.Tensor) -> torch.Tensor:
        hidden_states = self.dense(hidden_states)
        hidden_states = self.dropout_add(hidden_states, input_tensor, self.dropout.p, self.dropout.training)
        hidden_states = self.LayerNorm(hidden_states)
        return hidden_states

    return forward


def bert_sequence_parallel_forward_fn(shard_config: ShardConfig):

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

            - 1 for tokens that are **not masked**,
            - 0 for tokens that are **masked**.
        past_key_values (`tuple(tuple(torch.FloatTensor))` of length `config.n_layers` with each tuple having 4 tensors of shape `(batch_size, num_heads, sequence_length - 1, embed_size_per_head)`):
            Contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding.

            If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those that
            don't have their past key value states given to this model) of shape `(batch_size, 1)` instead of all
            `decoder_input_ids` of shape `(batch_size, sequence_length)`.
        use_cache (`bool`, *optional*):
            If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see
            `past_key_values`).
        """
        output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
        output_hidden_states = (output_hidden_states
                                if output_hidden_states is not None else self.config.output_hidden_states)
        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

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

        if input_ids is not None and inputs_embeds is not None:
            raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
        elif input_ids is not None:
            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:
            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 = 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)

        # 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,
        )

        # split the input tensor along sequence dimension
        # [batch_size, seq_len, hidden_size] -> [batch_size, seq_len/TP_size, hidden_size]
        embedding_output = split_forward_gather_backward(embedding_output,
                                                         dim=1,
                                                         process_group=shard_config.tensor_parallel_process_group)
        if encoder_hidden_states is not None:
            encoder_hidden_states = split_forward_gather_backward(
                encoder_hidden_states, dim=1, process_group=shard_config.tensor_parallel_process_group)

        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]

        # When sequence parallelism done, gather the output tensor in forward and split it in backward
        sequence_output = gather_forward_split_backward(sequence_output,
                                                        dim=1,
                                                        process_group=shard_config.tensor_parallel_process_group)

        pooled_output = self.pooler(sequence_output) if self.pooler is not None else None

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

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

    return forward