Instructions to use PaddlePaddle/PaddleOCR-VL-1.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PaddleOCR
How to use PaddlePaddle/PaddleOCR-VL-1.5 with PaddleOCR:
# See https://www.paddleocr.ai/latest/version3.x/pipeline_usage/PaddleOCR-VL.html to installation from paddleocr import PaddleOCRVL pipeline = PaddleOCRVL(pipeline_version="v1.5") output = pipeline.predict("path/to/document_image.png") for res in output: res.print() res.save_to_json(save_path="output") res.save_to_markdown(save_path="output") - Notebooks
- Google Colab
- Kaggle
Repetition makes this unusable
Added variations of small to large repetition_penalty and/or presence_penalty and it continuously had problems. I stayed with the recommended greedy decoding but gave low temp a try and it still showed issues.
Seems like this must be an inherent issue with the model? Has anyone seen this work without eventually getting into a repeat loop?
This seems to happen mainly with table structure or visual elements where it wants to use "[-|_|.]" to represent something. This seems like its related to table parsing but also happens on representing visual content or spacing. I'm using the "OCR" task.
Hosted on a 4090 through vllm.
Yes i am seeing same problem, havent got chance to work on trying out different settings yet. I tried with various files, here are some repetitions i noticed
$1,500 $1,500 $1,500 $1,500
ADDITIONAL COST CONSIDERATIONS are not paid directly
It is not a单独文件,而是一份完整的文件