optimum/habana/transformers/models/gpt2/modeling_gpt2.py

from typing import Optional, Tuple, Union

import torch
from torch.nn import CrossEntropyLoss
from transformers.modeling_outputs import BaseModelOutputWithPastAndCrossAttentions, CausalLMOutputWithCrossAttentions
from transformers.models.gpt2.modeling_gpt2 import (
    GPT2MLP,
    GPT2Attention,
    GPT2DoubleHeadsModel,
    GPT2DoubleHeadsModelOutput,
    GPT2LMHeadModel,
    eager_attention_forward,
    logger,
)


class GaudiGPT2Attention(GPT2Attention):
    """
    Copied from GPT2Attention: https://github.com/huggingface/transformers/blob/main/src/transformers/models/gpt2/modeling_gpt2.py
    The only differences are:
    - optimize KV cache
    """

    def _upcast_and_reordered_attn(self, query, key, value, attention_mask=None, head_mask=None):
        key = key.contiguous()
        value = value.contiguous()
        # Use `torch.baddbmm` (a bit more efficient w/ alpha param for scaling -- from Megatron-LM)
        bsz, num_heads, q_seq_len, dk = query.size()
        _, _, k_seq_len, _ = key.size()

        # Preallocate attn_weights for `baddbmm`
        attn_weights = torch.empty(bsz * num_heads, q_seq_len, k_seq_len, dtype=torch.float32, device=query.device)

        # Compute Scale Factor
        scale_factor = 1.0
        if self.scale_attn_weights:
            scale_factor /= float(value.size(-1)) ** 0.5

        if self.scale_attn_by_inverse_layer_idx:
            scale_factor /= float(self.layer_idx + 1)

        q, k = query.reshape(-1, q_seq_len, dk), key.transpose(-1, -2).reshape(-1, dk, k_seq_len)
        attn_weights = torch.baddbmm(attn_weights, q.float(), k.float(), beta=0, alpha=scale_factor)
        attn_weights = attn_weights.reshape(bsz, num_heads, q_seq_len, k_seq_len)

        if not self.is_cross_attention:
            # if only "normal" attention layer implements causal mask
            query_length, key_length = query.size(-2), key.size(-2)
            causal_mask = self.bias[:, :, key_length - query_length : key_length, :key_length]
            mask_value = torch.finfo(attn_weights.dtype).min
            # Need to be a tensor, otherwise we get error: `RuntimeError: expected scalar type float but found double`.
            # Need to be on the same device, otherwise `RuntimeError: ..., x and y to be on the same device`
            mask_value = torch.tensor(mask_value, dtype=attn_weights.dtype, device=attn_weights.device)
            attn_weights = torch.where(causal_mask, attn_weights, mask_value)

        if attention_mask is not None:
            # Apply the attention mask
            attn_weights = attn_weights + attention_mask

        attn_weights = torch.nn.functional.softmax(attn_weights, dim=-1)

        # Downcast (if necessary) back to V's dtype (if in mixed-precision) -- No-Op if otherwise
        if attn_weights.dtype != torch.float32:
            raise RuntimeError("Error with upcasting, attn_weights does not have dtype torch.float32")
        attn_weights = attn_weights.type(value.dtype)
        attn_weights = self.attn_dropout(attn_weights)

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

        attn_output = torch.matmul(attn_weights, value)
        attn_output = attn_output.transpose(1, 2)

        return attn_output, attn_weights

    def forward(
        self,
        hidden_states: Optional[Tuple[torch.FloatTensor]],
        layer_past: Optional[Tuple[torch.Tensor]] = None,
        attention_mask: Optional[torch.FloatTensor] = None,
        head_mask: Optional[torch.FloatTensor] = None,
        encoder_hidden_states: Optional[torch.Tensor] = None,
        encoder_attention_mask: Optional[torch.FloatTensor] = None,
        use_cache: Optional[bool] = False,
        output_attentions: Optional[bool] = False,
        token_idx: Optional[torch.Tensor] = None,
    ) -> Tuple[Union[torch.Tensor, Tuple[torch.Tensor]], ...]:
        if encoder_hidden_states is not None:
            if not hasattr(self, "q_attn"):
                raise ValueError(
                    "If class is used as cross attention, the weights `q_attn` have to be defined. "
                    "Please make sure to instantiate class with `GPT2Attention(..., is_cross_attention=True)`."
                )

            query_states = self.q_attn(hidden_states)
            key_states, value_states = self.c_attn(encoder_hidden_states).split(self.split_size, dim=2)
            attention_mask = encoder_attention_mask
        else:
            query_states, key_states, value_states = self.c_attn(hidden_states).split(self.split_size, dim=2)

        shape_q = (*query_states.shape[:-1], -1, self.head_dim)
        shape_kv = (*key_states.shape[:-1], -1, self.head_dim)

        query_states = query_states.view(shape_q).transpose(1, 2).contiguous()
        key_states = key_states.view(shape_kv).transpose(1, 2).contiguous()
        value_states = value_states.view(shape_kv).transpose(1, 2).contiguous()

        if layer_past is not None:
            past_key, past_value = layer_past
            if token_idx is not None:
                past_key.index_copy_(2, token_idx - 1, key_states)
                past_value.index_copy_(2, token_idx - 1, value_states)
                key_states = past_key
                value_states = past_value
            else:
                key_states = torch.cat((past_key, key_states), dim=-2)
                value_states = torch.cat((past_value, value_states), dim=-2)

        if use_cache is True:
            present = (key_states, value_states)
        else:
            present = None

        if self.reorder_and_upcast_attn:
            attn_output, attn_weights = self._upcast_and_reordered_attn(
                query_states, key_states, value_states, attention_mask, head_mask
            )
        else:
            attn_output, attn_weights = eager_attention_forward(
                self,
                query_states,
                key_states,
                value_states,
                attention_mask,
                head_mask=head_mask,
                dropout=self.attn_dropout.p if self.training else 0.0,
            )

        attn_output = attn_output.reshape(*attn_output.shape[:-2], -1).contiguous()
        attn_output = self.c_proj(attn_output)
        attn_output = self.resid_dropout(attn_output)

        outputs = (attn_output, present)
        if output_attentions:
            outputs += (attn_weights,)

        return outputs  # a, present, (attentions)


class GaudiGPT2Block(torch.nn.Module):
    def __init__(self, config, layer_idx=None):
        super().__init__()
        hidden_size = config.hidden_size
        inner_dim = config.n_inner if config.n_inner is not None else 4 * hidden_size
        attention_class = GaudiGPT2Attention

        self.ln_1 = torch.nn.LayerNorm(hidden_size, eps=config.layer_norm_epsilon)
        self.attn = attention_class(config=config, layer_idx=layer_idx)
        self.ln_2 = torch.nn.LayerNorm(hidden_size, eps=config.layer_norm_epsilon)

        if config.add_cross_attention:
            self.crossattention = attention_class(config=config, is_cross_attention=True, layer_idx=layer_idx)
            self.ln_cross_attn = torch.nn.LayerNorm(hidden_size, eps=config.layer_norm_epsilon)

        self.mlp = GPT2MLP(inner_dim, config)

    def forward(
        self,
        hidden_states: Optional[Tuple[torch.FloatTensor]],
        layer_past: Optional[Tuple[torch.Tensor]] = None,
        attention_mask: Optional[torch.FloatTensor] = None,
        head_mask: Optional[torch.FloatTensor] = None,
        encoder_hidden_states: Optional[torch.Tensor] = None,
        encoder_attention_mask: Optional[torch.FloatTensor] = None,
        use_cache: Optional[bool] = False,
        output_attentions: Optional[bool] = False,
        token_idx: Optional[torch.Tensor] = None,
    ) -> Union[Tuple[torch.Tensor], Optional[Tuple[torch.Tensor, Tuple[torch.FloatTensor, ...]]]]:
        """
        Copied from GPT2Block.forward: https://github.com/huggingface/transformers/blob/main/src/transformers/models/gpt2/modeling_gpt2.py
        The only differences are:
        - add new args token_idx
        """

        residual = hidden_states
        hidden_states = self.ln_1(hidden_states)

        attn_outputs = self.attn(
            hidden_states,
            layer_past=layer_past,
            attention_mask=attention_mask,
            head_mask=head_mask,
            use_cache=use_cache,
            output_attentions=output_attentions,
            token_idx=token_idx,
        )
        attn_output = attn_outputs[0]  # output_attn: a, present, (attentions)
        outputs = attn_outputs[1:]
        # residual connection
        hidden_states = attn_output + residual

        if encoder_hidden_states is not None:
            # add one self-attention block for cross-attention
            if not hasattr(self, "crossattention"):
                raise ValueError(
                    f"If `encoder_hidden_states` are passed, {self} has to be instantiated with "
                    "cross-attention layers by setting `config.add_cross_attention=True`"
                )
            residual = hidden_states
            hidden_states = self.ln_cross_attn(hidden_states)
            cross_attn_outputs = self.crossattention(
                hidden_states,
                attention_mask=attention_mask,
                head_mask=head_mask,
                encoder_hidden_states=encoder_hidden_states,
                encoder_attention_mask=encoder_attention_mask,
                output_attentions=output_attentions,
            )
            attn_output = cross_attn_outputs[0]
            # residual connection
            hidden_states = residual + attn_output
            outputs = outputs + cross_attn_outputs[2:]  # add cross attentions if we output attention weights

        residual = hidden_states
        hidden_states = self.ln_2(hidden_states)

        feed_forward_hidden_states = self.mlp(hidden_states)
        # residual connection
        hidden_states = residual + feed_forward_hidden_states

        if use_cache:
            outputs = (hidden_states,) + outputs
        else:
            outputs = (hidden_states,) + outputs[1:]

        return outputs  # hidden_states, present, (attentions, cross_attentions)


def gaudi_gpt2_forward(
    self,
    input_ids: Optional[torch.LongTensor] = None,
    past_key_values: Optional[Tuple[Tuple[torch.Tensor]]] = None,
    attention_mask: Optional[torch.FloatTensor] = None,
    token_type_ids: Optional[torch.LongTensor] = None,
    position_ids: Optional[torch.LongTensor] = None,
    head_mask: Optional[torch.FloatTensor] = None,
    inputs_embeds: Optional[torch.FloatTensor] = None,
    encoder_hidden_states: Optional[torch.Tensor] = None,
    encoder_attention_mask: Optional[torch.FloatTensor] = None,
    use_cache: Optional[bool] = None,
    output_attentions: Optional[bool] = None,
    output_hidden_states: Optional[bool] = None,
    return_dict: Optional[bool] = None,
    token_idx: Optional[torch.Tensor] = None,
) -> Union[Tuple, BaseModelOutputWithPastAndCrossAttentions]:
    """
    Copied from GPT2Model.forward: https://github.com/huggingface/transformers/blob/main/src/transformers/models/gpt2/modeling_gpt2.py
    The only differences are:
    - disable autocast for attention_mask
    - add new args token_idx
    """

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

    if input_ids is not None and inputs_embeds is not None:
        raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
    elif input_ids is not None:
        self.warn_if_padding_and_no_attention_mask(input_ids, attention_mask)
        input_shape = input_ids.size()
        input_ids = input_ids.view(-1, input_shape[-1])
        batch_size = input_ids.shape[0]
    elif inputs_embeds is not None:
        input_shape = inputs_embeds.size()[:-1]
        batch_size = inputs_embeds.shape[0]
    else:
        raise ValueError("You have to specify either input_ids or inputs_embeds")

    device = input_ids.device if input_ids is not None else inputs_embeds.device

    if token_type_ids is not None:
        token_type_ids = token_type_ids.view(-1, input_shape[-1])

    if past_key_values is None:
        past_length = 0
        past_key_values = tuple([None] * len(self.h))
    else:
        past_length = past_key_values[0][0].size(-2)
    if position_ids is None:
        position_ids = torch.arange(past_length, input_shape[-1] + past_length, dtype=torch.long, device=device)
        position_ids = position_ids.unsqueeze(0)

    if inputs_embeds is None:
        inputs_embeds = self.wte(input_ids)
    position_embeds = self.wpe(position_ids)
    hidden_states = inputs_embeds + position_embeds.to(inputs_embeds.device)

    # GPT2Attention mask.
    attention_mask = attention_mask.view(batch_size, -1) if attention_mask is not None else None
    if attention_mask is not None:
        # We create a 3D attention mask from a 2D tensor mask.
        # Sizes are [batch_size, 1, 1, to_seq_length]
        # So we can broadcast to [batch_size, num_heads, from_seq_length, to_seq_length]
        # this attention mask is more simple than the triangular masking of causal attention
        # used in OpenAI GPT, we just need to prepare the broadcast dimension here.
        attention_mask = attention_mask[:, None, None, :]

        # Since attention_mask is 1.0 for positions we want to attend and 0.0 for
        # masked positions, this operation will create a tensor which is 0.0 for
        # positions we want to attend and the dtype's smallest value for masked positions.
        # Since we are adding it to the raw scores before the softmax, this is
        # effectively the same as removing these entirely.
        attention_mask = attention_mask.to(dtype=self.dtype)  # fp16 compatibility

        with torch.autocast(enabled=False, device_type="hpu"):
            attention_mask = (1.0 - attention_mask) * torch.finfo(self.dtype).min

    # 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.add_cross_attention 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_attention_mask = self.invert_attention_mask(encoder_attention_mask)
    else:
        encoder_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
    # head_mask has shape n_layer x batch x n_heads x N x N
    head_mask = self.get_head_mask(head_mask, self.config.n_layer)

    if token_type_ids is not None:
        token_type_embeds = self.wte(token_type_ids)
        hidden_states = hidden_states + token_type_embeds

    hidden_states = self.drop(hidden_states)

    output_shape = (-1,) + input_shape[1:] + (hidden_states.size(-1),)

    if self.gradient_checkpointing and self.training:
        if use_cache:
            logger.warning_once(
                "`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`..."
            )
            use_cache = False

    presents = () if use_cache else None
    all_self_attentions = () if output_attentions else None
    all_cross_attentions = () if output_attentions and self.config.add_cross_attention else None
    all_hidden_states = () if output_hidden_states else None
    for i in range(len(self.h)):
        block, layer_past = self.h[i], past_key_values[i]
        # Model parallel
        if self.model_parallel:
            torch.cuda.set_device(hidden_states.device)
            # Ensure layer_past is on same device as hidden_states (might not be correct)
            if layer_past is not None:
                layer_past = tuple(past_state.to(hidden_states.device) for past_state in layer_past)
            # Ensure that attention_mask is always on the same device as hidden_states
            if attention_mask is not None:
                attention_mask = attention_mask.to(hidden_states.device)
            if isinstance(head_mask, torch.Tensor):
                head_mask = head_mask.to(hidden_states.device)
        if output_hidden_states:
            all_hidden_states = all_hidden_states + (hidden_states,)

        if self.gradient_checkpointing and self.training:
            outputs = self._gradient_checkpointing_func(
                block.__call__,
                hidden_states,
                None,
                attention_mask,
                head_mask[i],
                encoder_hidden_states,
                encoder_attention_mask,
                use_cache,
                output_attentions,
                None,
            )
        else:
            outputs = block(
                hidden_states,
                layer_past=layer_past,
                attention_mask=attention_mask,
                head_mask=head_mask[i],
                encoder_hidden_states=encoder_hidden_states,
                encoder_attention_mask=encoder_attention_mask,
                use_cache=use_cache,
                output_attentions=output_attentions,
                token_idx=token_idx,
            )

        hidden_states = outputs[0]
        if use_cache is True:
            presents = presents + (outputs[1],)

        if output_attentions:
            all_self_attentions = all_self_attentions + (outputs[2 if use_cache else 1],)
            if self.config.add_cross_attention:
                all_cross_attentions = all_cross_attentions + (outputs[3 if use_cache else 2],)

        # Model Parallel: If it's the last layer for that device, put things on the next device
        if self.model_parallel:
            for k, v in self.device_map.items():
                if i == v[-1] and "cuda:" + str(k) != self.last_device:
                    hidden_states = hidden_states.to("cuda:" + str(k + 1))

    hidden_states = self.ln_f(hidden_states)

    hidden_states = hidden_states.view(output_shape)
    # Add last hidden state
    if output_hidden_states:
        all_hidden_states = all_hidden_states + (hidden_states,)

    if not return_dict:
        return tuple(
            v
            for v in [hidden_states, presents, all_hidden_states, all_self_attentions, all_cross_attentions]
            if v is not None
        )

    return BaseModelOutputWithPastAndCrossAttentions(
        last_hidden_state=hidden_states,
        past_key_values=presents,
        hidden_states=all_hidden_states,
        attentions=all_self_attentions,
        cross_attentions=all_cross_attentions,
    )


class GaudiGPT2LMHeadModel(GPT2LMHeadModel):
    """
    Copied from GPT2LMHeadModel: https://github.com/huggingface/transformers/blob/main/src/transformers/models/gpt2/modeling_gpt2.py
    The only differences are:
    - add new args token_idx
    """

    def prepare_inputs_for_generation(
        self, input_ids, past_key_values=None, inputs_embeds=None, token_idx=None, **kwargs
    ):
        token_type_ids = kwargs.get("token_type_ids", None)
        # Omit tokens covered by past_key_values
        if past_key_values:
            if token_idx is not None:
                idx = token_idx + kwargs.get("inputs_embeds_offset", 0) - 1
                input_ids = torch.index_select(input_ids, 1, idx)
            else:
                past_length = past_key_values[0][0].shape[2]

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

                input_ids = input_ids[:, remove_prefix_length:]

            if token_type_ids is not None:
                token_type_ids = token_type_ids[:, -input_ids.shape[1] :]

        attention_mask = kwargs.get("attention_mask", None)
        position_ids = kwargs.get("position_ids", None)

        if attention_mask is not None and position_ids is None:
            # create position_ids on the fly for batch generation
            position_ids = attention_mask.long().cumsum(-1) - 1
            position_ids.masked_fill_(attention_mask == 0, 1)
            if past_key_values:
                if token_idx is not None:
                    position_ids = torch.index_select(position_ids, 1, token_idx - 1)
                else:
                    position_ids = position_ids[:, -input_ids.shape[1] :]

        else:
            position_ids = None

        # if `inputs_embeds` are passed, we only want to use them in the 1st generation step
        if inputs_embeds is not None and past_key_values is None:
            model_inputs = {"inputs_embeds": inputs_embeds}
        else:
            model_inputs = {"input_ids": input_ids}
        model_inputs.update(
            {
                "past_key_values": past_key_values,
                "use_cache": kwargs.get("use_cache"),
                "position_ids": position_ids,
                "attention_mask": attention_mask,
                "token_type_ids": token_type_ids,
                "token_idx": token_idx,
            }
        )
        return model_inputs

    def forward(
        self,
        input_ids: Optional[torch.LongTensor] = None,
        past_key_values: Optional[Tuple[Tuple[torch.Tensor]]] = None,
        attention_mask: Optional[torch.FloatTensor] = None,
        token_type_ids: Optional[torch.LongTensor] = None,
        position_ids: Optional[torch.LongTensor] = None,
        head_mask: Optional[torch.FloatTensor] = None,
        inputs_embeds: Optional[torch.FloatTensor] = None,
        encoder_hidden_states: Optional[torch.Tensor] = None,
        encoder_attention_mask: Optional[torch.FloatTensor] = None,
        labels: Optional[torch.LongTensor] = None,
        use_cache: Optional[bool] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
        token_idx: Optional[torch.Tensor] = None,
        **kwargs,
    ) -> Union[Tuple, CausalLMOutputWithCrossAttentions]:
        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        transformer_outputs = self.transformer(
            input_ids,
            past_key_values=past_key_values,
            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,
            use_cache=use_cache,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
            token_idx=token_idx,
        )
        hidden_states = transformer_outputs[0]

        # Set device for model parallelism
        if self.model_parallel:
            torch.cuda.set_device(self.transformer.first_device)
            hidden_states = hidden_states.to(self.lm_head.weight.device)

        lm_logits = self.lm_head(hidden_states)

        loss = None
        if labels is not None:
            # Flatten the tokens
            loss = self.loss_function(
                lm_logits,
                labels,
                vocab_size=self.config.vocab_size,
                **kwargs,
            )

        if not return_dict:
            output = (lm_logits,) + transformer_outputs[1:]
            return ((loss,) + output) if loss is not None else output

        return CausalLMOutputWithCrossAttentions(
            loss=loss,
            logits=lm_logits,
            past_key_values=transformer_outputs.past_key_values,
            hidden_states=transformer_outputs.hidden_states,
            attentions=transformer_outputs.attentions,
            cross_attentions=transformer_outputs.cross_attentions,
        )


class GaudiGPT2DoubleHeadsModel(GPT2DoubleHeadsModel):
    """
    Copied from GPT2DoubleHeadsModel: https://github.com/huggingface/transformers/blob/v4.40.2/src/transformers/models/gpt2/modeling_gpt2.py#L1377
    The only differences are:
    - add new args token_idx to support static shapes
    """

    def prepare_inputs_for_generation(
        self, input_ids, inputs_embeds=None, past_key_values=None, token_idx=None, **kwargs
    ):
        token_type_ids = kwargs.get("token_type_ids", None)
        # Omit tokens covered by past_key_values
        if past_key_values:
            if token_idx is not None:
                idx = token_idx - 1
                if "inputs_embeds_offset" in kwargs:
                    idx = idx + kwargs["inputs_embeds_offset"]
                input_ids = torch.index_select(input_ids, 1, idx)
            else:
                past_length = past_key_values[0][0].shape[2]

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

                input_ids = input_ids[:, remove_prefix_length:]

            if token_type_ids is not None:
                token_type_ids = token_type_ids[:, -input_ids.shape[1] :]

        attention_mask = kwargs.get("attention_mask", None)
        position_ids = kwargs.get("position_ids", None)

        if attention_mask is not None and position_ids is None:
            # create position_ids on the fly for batch generation
            position_ids = attention_mask.long().cumsum(-1) - 1
            position_ids.masked_fill_(attention_mask == 0, 1)
            if past_key_values:
                if token_idx is not None:
                    position_ids = torch.index_select(position_ids, 1, token_idx - 1)
                else:
                    position_ids = position_ids[:, -input_ids.shape[1] :]
        else:
            position_ids = None

        # if `inputs_embeds` are passed, we only want to use them in the 1st generation step
        if inputs_embeds is not None and past_key_values is None:
            model_inputs = {"inputs_embeds": inputs_embeds}
        else:
            model_inputs = {"input_ids": input_ids.contiguous()}

        model_inputs.update(
            {
                "past_key_values": past_key_values,
                "use_cache": kwargs.get("use_cache"),
                "position_ids": position_ids,
                "attention_mask": attention_mask,
                "token_type_ids": token_type_ids,
                "token_idx": token_idx,
            }
        )

        return model_inputs

    def forward(
        self,
        input_ids: Optional[torch.LongTensor] = None,
        past_key_values: Optional[Tuple[Tuple[torch.Tensor]]] = None,
        attention_mask: Optional[torch.FloatTensor] = None,
        token_type_ids: Optional[torch.LongTensor] = None,
        position_ids: Optional[torch.LongTensor] = None,
        head_mask: Optional[torch.FloatTensor] = None,
        inputs_embeds: Optional[torch.FloatTensor] = None,
        mc_token_ids: Optional[torch.LongTensor] = None,
        labels: Optional[torch.LongTensor] = None,
        mc_labels: Optional[torch.LongTensor] = None,
        use_cache: Optional[bool] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
        token_idx: Optional[torch.Tensor] = None,
        **kwargs,
    ) -> Union[Tuple, GPT2DoubleHeadsModelOutput]:
        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        transformer_outputs = self.transformer(
            input_ids,
            past_key_values=past_key_values,
            attention_mask=attention_mask,
            token_type_ids=token_type_ids,
            position_ids=position_ids,
            head_mask=head_mask,
            inputs_embeds=inputs_embeds,
            use_cache=use_cache,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
            token_idx=token_idx,
        )

        hidden_states = transformer_outputs[0]

        # Set device for model parallelism
        if self.model_parallel:
            torch.cuda.set_device(self.transformer.first_device)
            hidden_states = hidden_states.to(self.lm_head.weight.device)

        lm_logits = self.lm_head(hidden_states)
        mc_logits = self.multiple_choice_head(hidden_states, mc_token_ids).squeeze(-1)

        mc_loss = None
        if mc_labels is not None:
            loss_fct = CrossEntropyLoss()
            mc_loss = loss_fct(mc_logits.view(-1, mc_logits.size(-1)), mc_labels.view(-1))
        lm_loss = None
        if labels is not None:
            labels = labels.to(lm_logits.device)
            shift_logits = lm_logits[..., :-1, :].contiguous()
            shift_labels = labels[..., 1:].contiguous()
            loss_fct = CrossEntropyLoss()
            lm_loss = loss_fct(shift_logits.view(-1, shift_logits.size(-1)), shift_labels.view(-1))

        if not return_dict:
            output = (lm_logits, mc_logits) + transformer_outputs[1:]
            if mc_loss is not None:
                output = (mc_loss,) + output
            return ((lm_loss,) + output) if lm_loss is not None else output

        return GPT2DoubleHeadsModelOutput(
            loss=lm_loss,
            mc_loss=mc_loss,
            logits=lm_logits,
            mc_logits=mc_logits,
            past_key_values=transformer_outputs.past_key_values,
            hidden_states=transformer_outputs.hidden_states,
            attentions=transformer_outputs.attentions,
        )