Method _reorder_cache

models/modeling_moss.py:722–733

This function is used to re-order the `past_key_values` cache if [`~PretrainedModel.beam_search`] or [`~PretrainedModel.beam_sample`] is called. This is required to match `past_key_values` with the correct beam_idx at every generation step.

(
        past_key_values: Tuple[Tuple[torch.Tensor]], beam_idx: torch.Tensor
    )

    @staticmethod
    def _reorder_cache(
        past_key_values: Tuple[Tuple[torch.Tensor]], beam_idx: torch.Tensor
    ) -> Tuple[Tuple[torch.Tensor]]:
        """
        This function is used to re-order the `past_key_values` cache if [`~PretrainedModel.beam_search`] or
        [`~PretrainedModel.beam_sample`] is called. This is required to match `past_key_values` with the correct
        beam_idx at every generation step.
        """
        return tuple(
            tuple(past_state.index_select(0, beam_idx.to(past_state.device)) for past_state in layer_past)
            for layer_past in past_key_values
        )

    def quantize(self, wbits, groupsize):
        from .quantization import quantize_with_gptq