janus/janusflow/models/processing_vlm.py [287:333]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        return input_ids, num_image_tokens

    def process_one(
        self,
        prompt: str = None,
        conversations: List[Dict[str, str]] = None,
        images: List[Image] = None,
        **kwargs,
    ):
        """

        Args:
            prompt (str): the formatted prompt;
            conversations (List[Dict]): conversations with a list of messages;
            images (List[ImageType]): the list of images;
            **kwargs:

        Returns:
            outputs (BaseProcessorOutput): the output of the processor,
                - input_ids (torch.LongTensor): [N + image tokens]
                - target_ids (torch.LongTensor): [N + image tokens]
                - images (torch.FloatTensor): [n_images, 3, H, W]
                - image_id (int): the id of the image token
                - num_image_tokens (List[int]): the number of image tokens
        """

        assert (
            prompt is None or conversations is None
        ), "prompt and conversations cannot be used at the same time."

        if prompt is None:
            # apply sft format
            sft_format = self.apply_sft_template_for_multi_turn_prompts(
                conversations=conversations,
                sft_format=self.sft_format,
                system_prompt=self.system_prompt,
            )
        else:
            sft_format = prompt

        # tokenize
        input_ids = self.tokenizer.encode(sft_format)
        input_ids = torch.LongTensor(input_ids)

        # add image tokens to the input_ids
        image_token_mask: torch.BoolTensor = input_ids == self.image_id
        image_indices = image_token_mask.nonzero()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



janus/models/processing_vlm.py [258:304]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        return input_ids, num_image_tokens

    def process_one(
        self,
        prompt: str = None,
        conversations: List[Dict[str, str]] = None,
        images: List[Image] = None,
        **kwargs,
    ):
        """

        Args:
            prompt (str): the formatted prompt;
            conversations (List[Dict]): conversations with a list of messages;
            images (List[ImageType]): the list of images;
            **kwargs:

        Returns:
            outputs (BaseProcessorOutput): the output of the processor,
                - input_ids (torch.LongTensor): [N + image tokens]
                - target_ids (torch.LongTensor): [N + image tokens]
                - images (torch.FloatTensor): [n_images, 3, H, W]
                - image_id (int): the id of the image token
                - num_image_tokens (List[int]): the number of image tokens
        """

        assert (
            prompt is None or conversations is None
        ), "prompt and conversations cannot be used at the same time."

        if prompt is None:
            # apply sft format
            sft_format = self.apply_sft_template_for_multi_turn_prompts(
                conversations=conversations,
                sft_format=self.sft_format,
                system_prompt=self.system_prompt,
            )
        else:
            sft_format = prompt

        # tokenize
        input_ids = self.tokenizer.encode(sft_format)
        input_ids = torch.LongTensor(input_ids)

        # add image tokens to the input_ids
        image_token_mask: torch.BoolTensor = input_ids == self.image_id
        image_indices = image_token_mask.nonzero()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -