search

DAMO-NLP-SG / Video-LLaMA

[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding
BSD 3-Clause "New" or "Revised" License
2.83k stars 263 forks source link

multi-cards training #141

Open gqsmmz opened 10 months ago

gqsmmz commented 10 months ago

Do you have code for single player multi card training? I couldn't find it in the train. py and dataset code, only the torch run instruction