OPT(Omni-Perception Pre-Trainer)是全场景感知预训练模型的简称,中文名字叫紫东太初,是中科院自动化和华为联合研发的多模态预训练模型,本仓是紫东太初十亿参数级别模型的MindSpore版本代码,包含预训练模型及多个下游任务模型。
OPT(Omni-Perception Pre-Trainer)是全场景感知预训练模型的简称,中文名字叫紫东太初,是中科院自动化和华为联合研发的多模态预训练模型,本仓是紫东太初十亿参数级别模型的MindSpore版本代码,包含预训练模型及多个下游任务模型。
用于将pytorch迁移到mindspore框架时两个模型输出精度的对比,帮助快速确认迁移前后模块是否存在错误。
Contributions last year: 111
Max continuous contributions: 4
Recent contributions: 1
Commits, issues, and pull requests will appear on your contribution graph. Only when the email address used for the commits in local configuration is associated with your GitOSC account, the commits' contribution will be counted.