近日，清华团队与智谱AI合作开源了一个名为CogVLM-17B的多模态模型。CogVLM-17B是目前多模态权威学术榜单上综合成绩第一的模型，在14个数据集上取得了state-of-the-art或者第二名的成绩。该模型是智谱AI和清华团队推出的一款具备高性能、高可靠性、高可扩展性的多模态大模型，可广泛应用于自然语言处理、计算机视觉、推荐系统等众多领域。
英文标题：
清华大学与智谱AI合作推出多模态大模型CogVLM
英文翻译：
Recently, Tsinghua University team and Zhipu AI cooperation open source a multi-modal model named CogVLM-17B, which is currently the first model with the highest comprehensive performance on the multi-modal authority academic ranking list, and achieved state-of-the-art or second place on 14 datasets. This model is a high-performance, high-reliability, and scalable multi-modal large model that can be widely applied in many fields such as natural language processing, computer vision, and recommendation systems.
【来源】https://www.jiqizhixin.com/articles/2023-10-12
Views: 1