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

Llama 2 7B #46

Closed roninio closed 8 months ago

roninio commented 1 year ago

Hi great project

I am trying to run it with Llama 2. I have followed the steps. I am getting Hallucinations.

Can it be done with Llama 2 7B ?

mmaaz60 commented 1 year ago

Hi @roninio,

Thank you for your interest in our work. Currently, we don't have a LLaMA-2 based pretrained model and in order to use Video-ChatGPT with LLaMA, you have train the model on our Video Instruction Dataset.

However, we may release LLaMA-2 based models soon. Stay Tuned, Thank you.