IDEA-CCNL/Ziya-Visual-Eval-Chinese
收藏资源简介:
--- license: apache-2.0 language: - zh pretty_name: Ziya-Visual-Eval-Chinese size_categories: - n<1K --- # 姜子牙-Visual中文评估数据集 Ziya-Visual-Eval-Chinese ### 数据介绍 Dataset Summary 数据集由[LLaVA](https://github.com/haotian-liu/LLaVA)评估集翻译而来,图片源来自coco数据集,用于评估多模态大模型的中文能力 Dataset translated from the [LLaVA](https://github.com/haotian-liu/LLaVA) evaluation set, image source from the coco dataset, used to evaluate the Chinese language capabilities of the multimodal large model. ### 语言 Languages 中文 Chinese ### 数据示例 Data Instances ```json {"question_id": 0, "image": "000000441147.jpg", "text": "图片中两个手提箱的颜色是什么?", "category": "conv"} ``` ### 数据字段 Data Fields - id: int - image: str - text: str - category: str ### 引用 Citation ``` @article{fengshenbang, author = {Jiaxing Zhang and Ruyi Gan and Junjie Wang and Yuxiang Zhang and Lin Zhang and Ping Yang and Xinyu Gao and Ziwei Wu and Xiaoqun Dong and Junqing He and Jianheng Zhuo and Qi Yang and Yongfeng Huang and Xiayu Li and Yanghan Wu and Junyu Lu and Xinyu Zhu and Weifeng Chen and Ting Han and Kunhao Pan and Rui Wang and Hao Wang and Xiaojun Wu and Zhongshen Zeng and Chongpei Chen}, title = {Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence}, journal = {CoRR}, volume = {abs/2209.02970}, year = {2022} } ```
许可证:Apache-2.0 语言: - 中文 数据集名称:姜子牙-视觉中文评估数据集(Ziya-Visual-Eval-Chinese) 样本量分类: - 样本量小于1000(n<1K) # 姜子牙-视觉中文评估数据集(Ziya-Visual-Eval-Chinese) ### 数据集概览 本数据集系基于[LLaVA](https://github.com/haotian-liu/LLaVA)评估集翻译整编而成,图片素材取自COCO(Common Objects in Context)数据集,旨在评估多模态大语言模型的中文语言能力。 ### 语言 中文 ### 数据示例 json {"question_id": 0, "image": "000000441147.jpg", "text": "图片中两个手提箱的颜色是什么?", "category": "conv"} ### 数据字段 - `id`:整数类型,代表样本编号 - `image`:字符串类型,对应图片文件名 - `text`:字符串类型,对应评估问题文本 - `category`:字符串类型,代表数据类别 ### 引用 @article{fengshenbang, author = {Jiaxing Zhang and Ruyi Gan and Junjie Wang and Yuxiang Zhang and Lin Zhang and Ping Yang and Xinyu Gao and Ziwei Wu and Xiaoqun Dong and Junqing He and Jianheng Zhuo and Qi Yang and Yongfeng Huang and Xiayu Li and Yanghan Wu and Junyu Lu and Xinyu Zhu and Weifeng Chen and Ting Han and Kunhao Pan and Rui Wang and Hao Wang and Xiaojun Wu and Zhongshen Zeng and Chongpei Chen}, title = {封神榜1.0:中文认知智能的基石}, journal = {CoRR}, volume = {abs/22.09.02970}, year = {2022} }
姜子牙-Visual中文评估数据集 Ziya-Visual-Eval-Chinese
数据介绍
数据集由LLaVA评估集翻译而来,图片源来自coco数据集,用于评估多模态大模型的中文能力。
语言
中文
数据示例
json {"question_id": 0, "image": "000000441147.jpg", "text": "图片中两个手提箱的颜色是什么?", "category": "conv"}
数据字段
- id: int
- image: str
- text: str
- category: str
引用
@article{fengshenbang, author = {Jiaxing Zhang and Ruyi Gan and Junjie Wang and Yuxiang Zhang and Lin Zhang and Ping Yang and Xinyu Gao and Ziwei Wu and Xiaoqun Dong and Junqing He and Jianheng Zhuo and Qi Yang and Yongfeng Huang and Xiayu Li and Yanghan Wu and Junyu Lu and Xinyu Zhu and Weifeng Chen and Ting Han and Kunhao Pan and Rui Wang and Hao Wang and Xiaojun Wu and Zhongshen Zeng and Chongpei Chen}, title = {Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence}, journal = {CoRR}, volume = {abs/2209.02970}, year = {2022} }




