How to use PaddlePaddle/PP-DocBee-7B with PaddleOCR:
# 1. See https://www.paddlepaddle.org.cn/en/install to install paddlepaddle # 2. pip install paddleocr from paddleocr import DocVLM model = DocVLM(model_name="PP-DocBee-7B") output = model.predict( input={"image": "path/to/image.png", "query": "Parsing this image and output the content in Markdown format."}, batch_size=1 ) for res in output: res.print() res.save_to_json(save_path="./output/res.json")
https://huggingface.co/PaddlePaddle/PP-DocBee-7B/resolve/main/merges.txt
hf download hf://PaddlePaddle/PP-DocBee-7B/merges.txt
curl -L -o merges.txt https://huggingface.co/PaddlePaddle/PP-DocBee-7B/resolve/main/merges.txt
