Warning: You are using a model of type llava to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.

[kydxh]

I have met "You are using a model of type llava to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors." when I try to inference llava-onevision. Addtionally, when I try to inference "llava-v1.6-vicuna-7b", similar warning is "You are using a model of type llava to instantiate a model of type llava_llama. This is not supported for all configurations of models and can yield errors."
I wonder if this will have an impact on model inference.

[terry-for-github]

This happened when you load a LLM model into a MLLM model. (i.e. MLLM.from_pretrained(LLM))
I think it should be printed when ur training the model, but not for inference. (unless you use model_base option)