SenseTime releases the general model "Scholar 2.5"
數(shù)據(jù)猿 | 2023-03-15 19:19
【數(shù)據(jù)猿導讀】 On March 14, Sense Time released the multi-modal multi-task general-purpose large model "Scholar (INTERN) 2.5".
On March 14, SenseTime released the multi-modal multi-task general-purpose large model "Scholar (INTERN) 2.5". It has 3 billion parameters and is a model with more than 65.0 mAP in the object detection benchmark data set COCO. The "Scholar 2.5" multi-modal general-purpose large model has been open-sourced on OpenGVLab, a general-purpose vision open source platform participated by SenseTime.
Relying on multiple breakthroughs in multi-modal multi-tasking processing capabilities, the graphic and text cross-modal open task processing capabilities of "Scholar 2.5" can provide efficient and accurate perception and understanding support for common scene tasks such as autonomous driving and robots. Artificial intelligence has taken a solid step forward. "Scholar" was jointly released by Shangtang Technology, Shanghai Artificial Intelligence Laboratory, Tsinghua University, Chinese University of Hong Kong, and Shanghai Jiaotong University for the first time in November 2021, and continues to be jointly developed.
From now on, the "Scholar 2.5" multi-modal general large-scale model has been open sourced in OpenGVLab, a general vision open source platform participated by SenseTime.
來源：數(shù)據(jù)猿
