optimum/exporters/ipex/modeling_utils.py [259:282]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    inputs_embeds: 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,
    **kwargs,
) -> Union[Tuple, BaseModelOutputWithPast]:
    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

    # retrieve input_ids and inputs_embeds
    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:
        batch_size, seq_length = input_ids.shape[:2]
    elif inputs_embeds is not None:
        batch_size, seq_length = inputs_embeds.shape[:2]
    else:
        raise ValueError("You have to specify either input_ids or inputs_embeds")
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



optimum/exporters/openvino/model_patcher.py [1414:1440]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    inputs_embeds: 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,
    **kwargs,
) -> Union[Tuple, BaseModelOutputWithPast]:
    from transformers.cache_utils import Cache, DynamicCache
    from transformers.modeling_attn_mask_utils import _prepare_4d_causal_attention_mask

    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

    # retrieve input_ids and inputs_embeds
    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:
        batch_size, seq_length = input_ids.shape[:2]
    elif inputs_embeds is not None:
        batch_size, seq_length = inputs_embeds.shape[:2]
    else:
        raise ValueError("You have to specify either input_ids or inputs_embeds")
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -