The output from running evaluate.py is garbled

[mingtouyizu]

[gordonhu608]

Thanks for the interest in our work. I have not encountered this issue before. Did you follow the correct procedures in preparing and downloading model weights? See here

BLIVA/README.md

Lines 305 to 317 in d99de3a

	## Prepare Weight
	1. BLIVA Vicuna 7B
	Our Vicuna version model is released at [here](https://huggingface.co/mlpc-lab/BLIVA_Vicuna). Download our model weight and specify the path in the model config [here](bliva/configs/models/bliva_vicuna7b.yaml#L8) at line 8.
	The LLM we used is the v0.1 version from Vicuna-7B. To prepare Vicuna's weight, please refer to our instruction [here](PrepareVicuna.md). Then, set the path to the vicuna weight in the model config file [here](bliva/configs/models/bliva_vicuna7b.yaml#L21) at Line 21.
	2. BLIVA FlanT5 XXL (Available for Commercial Use)
	The FlanT5 version model is released at [here](https://huggingface.co/mlpc-lab/BLIVA_FlanT5). Download our model weight and specify the path in the model config [here](bliva/configs/models/bliva_flant5xxl.yaml#L8) at line 8.
	The LLM weight for Flant5 will automatically begin to download from huggingface when running our inference code.

[mingtouyizu]

Thanks，I have got it.