# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨 # This file was automatically generated from src/transformers/models/deepseek_vl/modular_deepseek_vl.py. # Do NOT edit this file manually as any edits will be overwritten by the generation of # the file from the modular. If any change should be done, please apply the change to the # modular_deepseek_vl.py file directly. One of our CI enforces this. # 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨 # Copyright 2025 Deepseek AI and The HuggingFace Team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. from typing import Optional from ...configuration_utils import PretrainedConfig from ...utils import logging from ..auto import CONFIG_MAPPING, AutoConfig logger = logging.get_logger(__name__) class DeepseekVLConfig(PretrainedConfig): r""" This is the configuration class to store the configuration of a [`DeepseekVLModel`]. It is used to instantiate a DeepseekVL model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the DeepseekVL [deepseek-community/deepseek-vl-1.3b-chat](https://huggingface.co/deepseek-community/deepseek-vl-1.3b-chat) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: text_config (`Union[AutoConfig, dict]`, *optional*, defaults to `LlamaConfig`): The config object or dictionary of the text backbone. vision_config (`Union[AutoConfig, dict]`, *optional*, defaults to `SiglipVisionConfig`): The config object or dictionary of the vision backbone. image_token_id (`int`, *optional*, defaults to 100015): The index representing image tokens in the model's token vocabulary. Example: ```python >>> from transformers import DeepseekVLConfig, DeepseekVLModel >>> # Initializing a DeepseekVL deepseek-community/deepseek-vl-1.3b-chat style configuration >>> configuration = DeepseekVLConfig() >>> # Initializing a model (with random weights) from the deepseek-community/deepseek-vl-1.3b-chat style configuration >>> model = DeepseekVLModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```""" model_type = "deepseek_vl" sub_configs = {"text_config": AutoConfig, "vision_config": AutoConfig} def __init__( self, text_config: Optional[AutoConfig] = None, vision_config: Optional[AutoConfig] = None, image_token_id: int = 100015, **kwargs, ): super().__init__(**kwargs) if text_config is None: text_config = {} logger.info("`text_config` is `None`. Initializing the `LlamaConfig` with default values.") if vision_config is None: vision_config = {} logger.info("`vision_config` is `None`. Initializing the `SiglipVisionConfig` with default values.") if isinstance(text_config, dict): text_config["model_type"] = text_config.get("model_type", "llama") text_config = CONFIG_MAPPING[text_config["model_type"]](**text_config) if isinstance(vision_config, dict): vision_config["model_type"] = vision_config.get("model_type", "siglip_vision_model") vision_config = CONFIG_MAPPING[vision_config["model_type"]](**vision_config) self.text_config = text_config self.vision_config = vision_config self.image_token_id = image_token_id __all__ = ["DeepseekVLConfig"]