[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.
I have been trying to get the offline demo to work, but I come across this problem.
Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Killed
I am running on a linux cluster, and have performed what I believe the correct implementations. Do you know why it would be killed?