Mirrors/dots.ocr
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update README

Browse Source
This commit is contained in:
zhangwei13
2025-07-31 16:12:40 +08:00
parent 2db2279526
commit 96d06b9b15
1 changed files with 7 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+7 -4
View File
@@ -849,7 +849,7 @@ This is an inhouse benchmark which contain 1493 pdf images with 100 languages.
<td>Nanonets OCR</td> <td>Nanonets OCR</td>
<td>67.0</td> <td>67.0</td>
<td>68.6</td> <td>68.6</td>
<td><strong>77.7</strong></td> <td>77.7</td>
<td>39.5</td> <td>39.5</td>
<td>40.7</td> <td>40.7</td>
<td>69.9</td> <td>69.9</td>
@@ -1014,7 +1014,7 @@ pip install -e .
### Download Model Weights ### 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. > 💡**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 ```shell
python tools/download_model.py python3 tools/download_model.py
``` ```
@@ -1025,14 +1025,17 @@ The [Docker Image](https://hub.docker.com/r/rednotehilab/dots.ocr) is based on t
```shell ```shell
# You need to register model to vllm at first # 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"):$PYTHONPATH export PYTHONPATH=$(dirname "$hf_model_path"):$PYTHONPATH
sed -i '/^from vllm\.entrypoints\.cli\.main import main$/a\ sed -i '/^from vllm\.entrypoints\.cli\.main import main$/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 # 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 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 # vllm api demo
python3 ./demo/demo_vllm.py --prompt_mode prompt_layout_all_en python3 ./demo/demo_vllm.py --prompt_mode prompt_layout_all_en
``` ```