baichuanzhou
Results
4
comments of
baichuanzhou
same here
You can use the `load_pretrained_model` function. Check [here](https://github.com/haotian-liu/LLaVA/blob/main/llava/model/builder.py#L87). You need to: 1. pass a model-base argument, which is the base language model you used for your llava model. 2. pass...
Hey, adding cache_position=None to the forward method also works. Check [here](https://github.com/LLaVA-VL/LLaVA-NeXT/blob/inference/llava/model/language_model/llava_llama.py#L80C9-L80C23)