Zidong Taichu officially open-sourced ZDTaichu5.0-9b. The size of the model adapts to the landing requirements. In the general multi-modal large model within 10B parameters, the ability to understand space and embody is outstanding, and the general multi-modal ability remains at a high level, and the full link ability of perception, cognition, decision making and action is fully covered. What is more noteworthy is that this open source not only opens up model weights, but also discloses detailed data production plans, and has been verified in real physical scenarios such as scientific research automation and intelligent manufacturing. This open source means that domestic multi-modal models are moving from “understanding the digital world” to “understanding and acting in the physical world.”

Zidong Taichu officially open-sourced ZDTaichu5.0-9b. The size of the model adapts to the landing requirements. In the general multi-modal large model within 10B parameters, the ability to understand space and embody is outstanding, and the general multi-modal ability remains at a high level, and the full link ability of perception, cognition, decision making and action is fully covered. What is more noteworthy is that this open source not only opens up model weights, but also discloses detailed data production plans, and has been verified in real physical scenarios such as scientific research automation and intelligent manufacturing. This open source means that domestic multi-modal models are moving from “understanding the digital world” to “understanding and acting in the physical world.”