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
1.23k stars 108 forks source link

linear layer #31

Closed Adeelyousaf closed 1 year ago

Adeelyousaf commented 1 year ago

Hi, can you confirm the dimensions of the linear layer that you learned?

Kind Regards

hanoonaR commented 1 year ago

Hi @Adeelyousaf ,

Thank you for your interest in our work. The dimensions of the learned linear layer is: 1024 x 4096. Please let us know if you have any further questions.