configuration_penguinvl.py

"""PenguinVL model configuration."""

import importlib.util
import os.path as osp
from typing import Optional, Dict, Any

from transformers import PretrainedConfig, Qwen3Config

try:
    from .configuration_penguinvl_encoder import PenguinVLVisionEncoderConfig
except ModuleNotFoundError:
    spec = importlib.util.spec_from_file_location(
        "configuration_penguinvl_encoder",
        osp.join(osp.dirname(__file__), "configuration_penguinvl_encoder.py"),
    )
    configuration_penguinvl_encoder = importlib.util.module_from_spec(spec)
    spec.loader.exec_module(configuration_penguinvl_encoder)
    PenguinVLVisionEncoderConfig = getattr(
        configuration_penguinvl_encoder,
        "PenguinVLVisionEncoderConfig",
    )


class PenguinVLQwen3Config(Qwen3Config):

    model_type = "penguinvl_qwen3"
    sub_configs = {"vision_encoder_config": PenguinVLVisionEncoderConfig}

    def __init__(
        self,
        vision_encoder: Optional[str] = None,
        vision_encoder_config: Dict[str, Any] = {},
        vision_projector_type: str = "mlp2x_gelu",
        use_token_compression: bool = True,
        image_token_index: int = -1,
        **kwargs,
    ):
        super().__init__(**kwargs)
        self.model_type = "penguinvl_qwen3"

        self.vision_encoder = vision_encoder
        if vision_encoder_config is not None and not isinstance(vision_encoder_config, PretrainedConfig):
            vision_encoder_config = PenguinVLVisionEncoderConfig(**vision_encoder_config)
        self.vision_encoder_config = vision_encoder_config

        self.vision_projector_type = vision_projector_type
        self.use_token_compression = use_token_compression
        self.image_token_index = image_token_index