MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
Paper • 2307.16449 • Published • 17
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
checkpoints for
@article{song2023moviechat,
title={MovieChat: From Dense Token to Sparse Memory for Long Video Understanding},
author={Song, Enxin and Chai, Wenhao and Wang, Guanhong and Zhang, Yucheng and Zhou, Haoyang and Wu, Feiyang and Guo, Xun and Ye, Tian and Lu, Yan and Hwang, Jenq-Neng and others},
journal={arXiv preprint arXiv:2307.16449},
year={2023}
}
- 7B is the vicuna v0 ckpt after applying delta on llama.
- Others are the ckpts acquire from the link on GitHub.
Prepared checkpoints here so that people can better acquire their models
- Downloads last month
- 22
Install from pip and serve model
# Install vLLM from pip: pip install vllm# Start the vLLM server: vllm serve "lmms-lab/MovieChat-ckpt"# Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lmms-lab/MovieChat-ckpt", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'