def forward()

in ultravox/model/ultravox_model.py [0:0]

• 16 lines of code
• 2 McCabe index (conditional complexity)

    def forward(
        self,
        input_ids: torch.Tensor,
        audio_values: Optional[torch.FloatTensor] = None,
        inputs_embeds: Optional[torch.FloatTensor] = None,
        labels: Optional[torch.Tensor] = None,
        attention_mask: Optional[torch.Tensor] = None,
        audio_token_start_idx: Optional[torch.Tensor] = None,
        audio_lens: Optional[torch.Tensor] = None,
        audio_token_len: Optional[torch.Tensor] = None,
        audio_batch_size: Optional[torch.Tensor] = None,
        past_key_values: Optional[Union[Tuple, transformers.cache_utils.Cache]] = None,
        # the alt_* fields are needed for KL divergence loss
        alt_input_ids: Optional[torch.Tensor] = None,
        alt_attention_mask: Optional[torch.Tensor] = None,
        alt_labels: Optional[torch.Tensor] = None,
        **kwargs,