SWHL/ChineseOCRBench download history

SWHL/ChineseOCRBench is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 289 times (27 in the last 7 days), and 6,820 times in total. It ranks #50,894 among datasets by monthly downloads.

Chinese OCRBench 由于对于多模态LLM的OCR方向的评测集中，缺少专门中文OCR任务的评测，因此考虑专门做一个中文OCR任务的评测。 关注到On the Hidden Mystery of OCR in Large Multimodal Models工作中已经做了两个中文OCR任务的评测，于是，ChineseOCRBench仅仅是将该篇工作中提出的中文评测数据集提了出来，作为专门中文OCR评测基准。 使用方式 建议与MultimodalOCR评测脚本结合使用。 from datasets import load_dataset da

Models trained on ChineseOCRBench

2 models list it as training data.

• REILX/llava-Qwen2-7B-Instruct-Chinese-CLIP-v2 17 downloads in 30 days
• REILX/llava-Qwen2-7B-Instruct-Chinese-CLIP-v3 13 downloads in 30 days

Open SWHL/ChineseOCRBench on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.