def forward()

in pytorch_transformers/modeling_gpt2.py [0:0]


    def forward(self, input_ids, position_ids=None, token_type_ids=None, past=None, head_mask=None):
        if past is None:
            past_length = 0
            past = [None] * len(self.h)
        else:
            past_length = past[0][0].size(-2)
        if position_ids is None:
            position_ids = torch.arange(past_length, input_ids.size(-1) + past_length, dtype=torch.long, device=input_ids.device)
            position_ids = position_ids.unsqueeze(0).expand_as(input_ids)

        # 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
        if head_mask is not None:
            if head_mask.dim() == 1:
                head_mask = head_mask.unsqueeze(0).unsqueeze(0).unsqueeze(-1).unsqueeze(-1)
                head_mask = head_mask.expand(self.config.n_layer, -1, -1, -1, -1)
            elif head_mask.dim() == 2:
                head_mask = head_mask.unsqueeze(1).unsqueeze(-1).unsqueeze(-1)  # We can specify head_mask for each layer
            head_mask = head_mask.to(dtype=next(self.parameters()).dtype) # switch to fload if need + fp16 compatibility
        else:
            head_mask = [None] * self.config.n_layer

        input_shape = input_ids.size()
        input_ids = input_ids.view(-1, input_ids.size(-1))
        position_ids = position_ids.view(-1, position_ids.size(-1))

        inputs_embeds = self.wte(input_ids)
        position_embeds = self.wpe(position_ids)
        if token_type_ids is not None:
            token_type_ids = token_type_ids.view(-1, token_type_ids.size(-1))
            token_type_embeds = self.wte(token_type_ids)
        else:
            token_type_embeds = 0
        hidden_states = inputs_embeds + position_embeds + token_type_embeds
        hidden_states = self.drop(hidden_states)

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

        presents = ()
        all_attentions = []
        all_hidden_states = ()
        for i, (block, layer_past) in enumerate(zip(self.h, past)):
            if self.output_hidden_states:
                all_hidden_states = all_hidden_states + (hidden_states.view(*output_shape),)

            outputs = block(hidden_states, layer_past, head_mask[i])
            hidden_states, present = outputs[:2]
            presents = presents + (present,)

            if self.output_attentions:
                all_attentions.append(outputs[2])

        hidden_states = self.ln_f(hidden_states)

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

        outputs = (hidden_states, presents)
        if self.output_hidden_states:
            outputs = outputs + (all_hidden_states,)
        if self.output_attentions:
            # let the number of heads free (-1) so we can extract attention even after head pruning
            attention_output_shape = input_shape[:-1] + (-1,) + all_attentions[0].shape[-2:]
            all_attentions = tuple(t.view(*attention_output_shape) for t in all_attentions)
            outputs = outputs + (all_attentions,)
        return outputs  # last hidden state, presents, (all hidden_states), (attentions)