No module named 'llava.tf_utils'

[pribadihcr]

I run this demo script

python -W ignore llava/eval/run_vila.py \
    --model-path Efficient-Large-Model/VILA1.5-3b \
    --conv-mode vicuna_v1 \
    --query "<video>\n Please describe this video." \
    --video-file "demo.mp4"

got the following error:

ModuleNotFoundError: No module named 'llava.tf_utils'

[yaolug]

We can not reproduce this issue.

[royshan]

I got the same error.

[yaolug]

Have you followed the instruction to set up the environment?

https://github.com/NVlabs/VILA?tab=readme-ov-file#installation

[royshan]

Thank you for your reply!

I followed the instructions and ran the shell: ./environment_setup.sh.

Should I use the alternative multi-step setup commands?

On Wed, Jun 19, 2024 at 4:14 PM Yao Lu @.***> wrote:

Have you followed the instruction to set up the environment?

https://github.com/NVlabs/VILA?tab=readme-ov-file#installation

— Reply to this email directly, view it on GitHub https://github.com/Efficient-Large-Model/VILA/issues/59#issuecomment-2178048155, or unsubscribe https://github.com/notifications/unsubscribe-auth/AAELXYMYKUQAXSJVLFB7IWTZIE4YFAVCNFSM6AAAAABHTMOAWCVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDCNZYGA2DQMJVGU . You are receiving this because you commented.Message ID: @.***>

-- Roy Shan

/*

• No DMZ Between Dream and Reality... */

[Lyken17]

Note this repo is now being deprecated

For further questions and comments, please move to https://github.com/NVlabs/VILA