janus/janusflow/models/processing_vlm.py [50:90]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def __len__(self):
        return len(self.input_ids)


@dataclass
class BatchedVLChatProcessorOutput(DictOutput):
    sft_format: List[str]
    input_ids: torch.Tensor
    pixel_values: torch.Tensor
    attention_mask: torch.Tensor
    images_seq_mask: torch.BoolTensor
    images_emb_mask: torch.BoolTensor

    def to(self, device, dtype=torch.bfloat16):
        self.input_ids = self.input_ids.to(device)
        self.attention_mask = self.attention_mask.to(device)
        self.images_seq_mask = self.images_seq_mask.to(device)
        self.images_emb_mask = self.images_emb_mask.to(device)
        self.pixel_values = self.pixel_values.to(device=device, dtype=dtype)
        return self


class VLChatProcessor(ProcessorMixin):
    image_processor_class = "AutoImageProcessor"
    tokenizer_class = ("LlamaTokenizer", "LlamaTokenizerFast")

    attributes = ["image_processor", "tokenizer"]

    system_prompt = (
        "You are a helpful language and vision assistant. "
        "You are able to understand the visual content that the user provides, "
        "and assist the user with a variety of tasks using natural language."
    )

    def __init__(
        self,
        image_processor: VLMImageProcessor,
        tokenizer: LlamaTokenizerFast,
        image_tag: str = "<image_placeholder>",
        image_start_tag: str = "<begin_of_image>",
        image_end_tag: str = "<end_of_image>",
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



janus/models/processing_vlm.py [50:90]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def __len__(self):
        return len(self.input_ids)


@dataclass
class BatchedVLChatProcessorOutput(DictOutput):
    sft_format: List[str]
    input_ids: torch.Tensor
    pixel_values: torch.Tensor
    attention_mask: torch.Tensor
    images_seq_mask: torch.BoolTensor
    images_emb_mask: torch.BoolTensor

    def to(self, device, dtype=torch.bfloat16):
        self.input_ids = self.input_ids.to(device)
        self.attention_mask = self.attention_mask.to(device)
        self.images_seq_mask = self.images_seq_mask.to(device)
        self.images_emb_mask = self.images_emb_mask.to(device)
        self.pixel_values = self.pixel_values.to(device=device, dtype=dtype)
        return self


class VLChatProcessor(ProcessorMixin):
    image_processor_class = "AutoImageProcessor"
    tokenizer_class = ("LlamaTokenizer", "LlamaTokenizerFast")

    attributes = ["image_processor", "tokenizer"]

    system_prompt = (
        "You are a helpful language and vision assistant. "
        "You are able to understand the visual content that the user provides, "
        "and assist the user with a variety of tasks using natural language."
    )

    def __init__(
        self,
        image_processor: VLMImageProcessor,
        tokenizer: LlamaTokenizerFast,
        image_tag: str = "<image_placeholder>",
        image_start_tag: str = "<begin_of_image>",
        image_end_tag: str = "<end_of_image>",
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -