Xingyu-Zheng/Qwen-VL-Chat

模型描述 (Model Description)

将Qwen-VL-Chat的官方格式按现在常用的QKV格式进行了转换，便于进行统一的算法开发。精度已在多模态任务上上验证，能够对齐原始版本。

This repository converts the official Qwen-VL format into the commonly used QKV format, enabling more unified algorithm development. The converted version has been validated on multimodal tasks and achieves performance consistent with the original model.

使用协议 (License Agreement)

研究人员与开发者可使用Qwen-VL和Qwen-VL-Chat或进行二次开发。我们同样允许商业使用，具体细节请查看LICENSE。如需商用，请填写问卷申请。

Researchers and developers are free to use the codes and model weights of both Qwen-VL and Qwen-VL-Chat. We also allow their commercial use. Check our license at LICENSE for more details.