Question about the output

[DwanZhang-AI]

This is the output of the model.

python -W ignore llava/eval/run_vila.py
--model-path Efficient-Large-Model/Llama-3-VILA1.5-8b
--conv-mode llama_3
--query "\n Please describe the traffic condition."
--image-file "demo_images/av.png"

This is the inference code. Why the output is wrong?

[DwanZhang-AI]

BTW, I have muted the flash attention module.

[Lyken17]

seems works properly on my side, should not be a issue for flash-attn. Could you make sure you have done a fresh install following readme?

[vedernikovphoto]

BTW, I have muted the flash attention module.

Hi, can you please explain how did you turn it off? I have V100 and can't run with "flash attention" On. Thanks!

[liuyijiang1994]

same problem

[Lyken17]

Close due to inacitivity. We haven't fully tested VILA on old hardware.