YueFan1014 / VideoAgent

This is the official code of VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding (ECCV 2024)
Apache License 2.0
97 stars 5 forks source link

An error about using GPT-3.5 as main LLM #4

Closed yukio0321 closed 3 weeks ago

yukio0321 commented 2 months ago

Thank you very much for your work, but I have a question if I don't have GPT-4, how can I replace it with GPT3.5 to run this code?

YueFan1014 commented 3 weeks ago

We recommend using GPT-4o or other LLMs that have strong instruction following abilities for inference.