[Help] Using VILA1.5-40b model for Video Descriptions

[SidPad03]

Hi,

I am trying to use the VILA1.5-40b model for doing video inference. Below is the prompt I am using:

python -W ignore llava/eval/run_vila.py \
	--model-path Efficient-Large-Model/VILA1.5-40b \
	--conv-mode hermes-2 \
	--query "<video>\n Describe what is going on in this video." \
	--video-file “/scratch/spadma20/VILA/test-vids/vid1-example.mp4”

And the error I get is:

Assertion Error: video file is not found

I have also tried using a relative path for the video file but that didn't work either. I know that the video path is correct, so that is not the issue. Am I missing something here?

[Lyken17]

can u a attach a more detailed log information?