From 9c1b7c2e61dace9fa3e5b6e50cd6752a72ea8192 Mon Sep 17 00:00:00 2001 From: ai-modelscope Date: Fri, 1 Aug 2025 07:39:29 +0800 Subject: [PATCH] Upload README.md with huggingface_hub --- README.md | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index 76692e6..08b40b6 100644 --- a/README.md +++ b/README.md @@ -3,7 +3,12 @@ license: mit library_name: dots_ocr pipeline_tag: image-text-to-text tags: +- image-to-text - ocr +- document-parse +- layout +- table +- formula language: - en - zh @@ -20,7 +25,7 @@ language: dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Model -[![arXiv](https://img.shields.io/badge/Arxiv-dots.ocr-b31b1b.svg?logo=arXiv)]() +[![Blog](https://img.shields.io/badge/Blog-View_on_GitHub-333.svg?logo=github)](https://github.com/rednote-hilab/dots.ocr/blob/master/assets/blog.md) [![HuggingFace](https://img.shields.io/badge/HuggingFace%20Weights-black.svg?logo=HuggingFace)](https://huggingface.co/rednote-hilab/dots.ocr) @@ -861,7 +866,7 @@ This is an inhouse benchmark which contain 1493 pdf images with 100 languages. Nanonets OCR 67.0 68.6 -77.7 +77.7 39.5 40.7 69.9 @@ -1026,7 +1031,7 @@ pip install -e . ### Download Model Weights > 💡**Note:** Please use a directory name without periods (e.g., `DotsOCR` instead of `dots.ocr`) for the model save path. This is a temporary workaround pending our integration with Transformers. ```shell -python tools/download_model.py +python3 tools/download_model.py ``` @@ -1037,14 +1042,17 @@ The [Docker Image](https://hub.docker.com/r/rednotehilab/dots.ocr) is based on t ```shell # You need to register model to vllm at first -export hf_model_path=./weights/DotsOCR # Path to your downloaded model weights +python3 tools/download_model.py +export hf_model_path=./weights/DotsOCR # Path to your downloaded model weights, Please use a directory name without periods (e.g., `DotsOCR` instead of `dots.ocr`) for the model save path. This is a temporary workaround pending our integration with Transformers. export PYTHONPATH=$(dirname "$hf_model_path"):$PYTHONPATH sed -i '/^from vllm\.entrypoints\.cli\.main import main$/a\ -from DotsOCR import modeling_dots_ocr_vllm' `which vllm` +from DotsOCR import modeling_dots_ocr_vllm' `which vllm` # If you downloaded model weights by yourself, please replace `DotsOCR` by your model saved directory name, and remember to use a directory name without periods (e.g., `DotsOCR` instead of `dots.ocr`) # launch vllm server CUDA_VISIBLE_DEVICES=0 vllm serve ${hf_model_path} --tensor-parallel-size 1 --gpu-memory-utilization 0.95 --chat-template-content-format string --served-model-name model --trust-remote-code +# If you get a ModuleNotFoundError: No module named 'DotsOCR', please check the note above on the saved model directory name. + # vllm api demo python3 ./demo/demo_vllm.py --prompt_mode prompt_layout_all_en ```