configuration_FlashVLStatic.py

import transformers
from transformers import (Qwen2Config, Qwen2ForCausalLM, SiglipVisionConfig,
                          SiglipVisionModel, PretrainedConfig)
from transformers import AutoConfig
import copy

class FlashVLStaticConfig(PretrainedConfig):
    model_type = 'FlashVLStaticConfig'
    is_composition = True

    def __init__(
            self,
            vision_config=dict(model_type='siglip_vision_model'),
            llm_config=dict(architectures=['Qwen2ForCausalLM']),
            **kwargs
        ):
        super().__init__(**kwargs)
        self.vision_config = SiglipVisionConfig(**vision_config)
        self.llm_config = Qwen2Config(**llm_config)

    def to_dict(self):
        
        output = copy.deepcopy(self.__dict__)
        output['vision_config'] = self.vision_config.to_dict()
        output['llm_config'] = self.llm_config.to_dict()

        return output