jina-clip v2, a 0.9b multimodal embedding model with multilingual support of 89 languages, high image resolution at 512x512, and matryoshka representations.
jina-clip-v2是新发布的多模态嵌入模型,支持89种语言,图像分辨率提升至512x512,性能较v1提高3%。该模型结合文本和视觉编码器,适用于多种检索任务,表现优异。

jina-clip v2, a 0.9b multimodal embedding model with multilingual support of 89 languages, high image resolution at 512x512, and matryoshka representations.
jina-clip-v2是新发布的多模态嵌入模型,支持89种语言,图像分辨率提升至512x512,性能较v1提高3%。该模型结合文本和视觉编码器,适用于多种检索任务,表现优异。