search

mbzuai-oryx / Video-ChatGPT

[ACL 2024 🔥] Video-ChatGPT is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrained visual encoder adapted for spatiotemporal video representation. We also introduce a rigorous 'Quantitative Evaluation Benchmarking' for video-based conversational models.
https://mbzuai-oryx.github.io/Video-ChatGPT
Creative Commons Attribution 4.0 International
1.17k stars 102 forks source link

Cannot load './LLaVA-Lightening-7B-v1-1' #22

Closed msra-jqxu closed 1 year ago

msra-jqxu commented 1 year ago

Hi, I followed the instruction in offline_demo.md and saved the Video-ChatGPT weights and the LLaVA-Lightening-7B-v1-1 weights in the current directory. Then I used this command for Offline Demo: python video_chatgpt/demo/video_demo.py --model-name ./LLaVA-Lightening-7B-v1-1 --projection_path ./video_chatgpt-7B.bin but got an error: huggingface_hub.utils.validators.HFValidationError: Repo id must use alphanumeric chars or '-', '', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: './LLaVA-Lightening-7B-v1-1'. Is it the way I fill in --model_name wrong?

Thanks!

image

mmaaz60 commented 1 year ago

Hi @msra-jqxu,

Thank You for your interest in our work. I tried reproducing the issue you are facing but everything is working fine for me. Could you try hard-coding the arguments directly to the video_chatgpt/demo/video_demo.py file instead of passing as command line arguments?

Further, please have a look at the https://github.com/huggingface/diffusers/issues/736 and it may help in resolving the issue.

Please let me know if it works or you have any further questions. Thank You.

MaxGonzalezSaez-Diez commented 7 months ago

Same issue