mbzuai-oryx/VideoGPT-plus
Official Repository of paper VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding
PythonCC-BY-4.0
Issues
- 0
- 0
- 3
Simple Demo
#8 opened by Zeqing-Wang - 0
- 1
- 2
Phi3Model ImportError
#16 opened by zimenglan-sysu-512 - 0
You are using a model of type phi3 to instantiate a model of type VideoGPT+. This is not supported for all configurations of models and can yield errors.
#17 opened by dpramanik2289 - 0
Intermediate descriptions for vcg-plus_112k
#15 opened by Charleshhy - 1
Question about Training Time
#14 opened by Backdrop9019 - 3
Detailed Video Descriptions
#11 opened by ShiYaya - 2
About pre-training stage.
#10 opened by HJYao00 - 1
are you planning to relase the inference codes for VideoGPT-plus_LLaMA3-8B-8k and/or VideoGPT-plus_Vicuna-7B-4k
#5 opened by pritamqu - 5
full-parameter or lora?
#3 opened by Nastu-Ho - 6
- 1
- 5
In what order should I reproduce the paper?
#12 opened by rixejzvdl649 - 1
About downloading the datatset?
#13 opened by zimenglan-sysu-512 - 3
- 8
Performance on MVBench
#4 opened by NIneeeeeem - 5
You mean phi3 surpassed mistral7B?
#1 opened by MonolithFoundation