janus/janusflow/models/processing_vlm.py [241:281]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def add_image_token(
        self,
        image_indices: List[int],
        input_ids: torch.LongTensor,
    ):
        """

        Args:
            image_indices (List[int]): [index_0, index_1, ..., index_j]
            input_ids (torch.LongTensor): [N]

        Returns:
            input_ids (torch.LongTensor): [N + image tokens]
            num_image_tokens (torch.IntTensor): [n_images]
        """

        input_slices = []

        start = 0
        for index in image_indices:
            if self.add_special_token:
                end = index + 1
            else:
                end = index

            # original text tokens
            input_slices.append(input_ids[start:end])

            # add boi, image tokens, eoi and set the mask as False
            input_slices.append(self.image_start_id * torch.ones((1), dtype=torch.long))
            input_slices.append(
                self.image_id * torch.ones((self.num_image_tokens,), dtype=torch.long)
            )
            input_slices.append(self.image_end_id * torch.ones((1), dtype=torch.long))
            start = index + 1

        # the left part
        input_slices.append(input_ids[start:])

        # concat all slices
        input_ids = torch.cat(input_slices, dim=0)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



janus/models/processing_vlm.py [215:255]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def add_image_token(
        self,
        image_indices: List[int],
        input_ids: torch.LongTensor,
    ):
        """

        Args:
            image_indices (List[int]): [index_0, index_1, ..., index_j]
            input_ids (torch.LongTensor): [N]

        Returns:
            input_ids (torch.LongTensor): [N + image tokens]
            num_image_tokens (torch.IntTensor): [n_images]
        """

        input_slices = []

        start = 0
        for index in image_indices:
            if self.add_special_token:
                end = index + 1
            else:
                end = index

            # original text tokens
            input_slices.append(input_ids[start:end])

            # add boi, image tokens, eoi and set the mask as False
            input_slices.append(self.image_start_id * torch.ones((1), dtype=torch.long))
            input_slices.append(
                self.image_id * torch.ones((self.num_image_tokens,), dtype=torch.long)
            )
            input_slices.append(self.image_end_id * torch.ones((1), dtype=torch.long))
            start = index + 1

        # the left part
        input_slices.append(input_ids[start:])

        # concat all slices
        input_ids = torch.cat(input_slices, dim=0)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -