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

Offline models and dataset download #63

Closed KerolosAtef closed 8 months ago

KerolosAtef commented 11 months ago

could you provide a direct link to download the offline folder that contains models and data using wget

mmaaz60 commented 11 months ago

Hi @KerolosAtef,

Thank you for your interest in our work. Unfortunately, currently 'wget' links are not available. However, our model is available on HuggingFace and data annotations are available on HugginFace and videos are available as OneDrive link.

Base LLaVA Model: this link Video-ChatGPT Projection Weights: this link

Dataset Videos: this link Dataset Annotations: this link

KerolosAtef commented 11 months ago

Hi @mmaaz60 thank you for these links, if there is a link for the dataset videos in google drive it will be good because I can't download the data using terminal in this way, however in google drive, I will use gdown library. I'm using terminal because I want to download this dataset to a server which hasn't a GUI.

mmaaz60 commented 11 months ago

Hi @KerolosAtef,

You may use this gdrive link. Thanks

KerolosAtef commented 11 months ago

Great, thank you very much, only the last thing, could you make it access to everyone with the link because gdown only works for the public links.

mmaaz60 commented 11 months ago

Great, thank you very much, only the last thing, could you make it access to everyone with the link because gdown only works for the public links.

Can you try this link?