modeling_llamavision.py

# https://huggingface.co/qresearch/llama-3.1-8B-vision-378/blob/main/configuration_llamavision.py

from transformers import PretrainedConfig, LlamaConfig, SiglipVisionConfig


class LlamavisionConfig(PretrainedConfig):
    model_type = "llamavision"

    def __init__(self, **kwargs):
        self.text_config = LlamaConfig(**kwargs.pop("text_config", {}))
        self.vision_config = SiglipVisionConfig(**kwargs.pop("vision_config", {}))
        super().__init__(**kwargs)