autodl 安装modelscope OCR 模型 dots_ocr 笔记心得

bash 复制代码

cd autodl-tmp

root@autodl-container-14e54cad63-9b7ce591:~/autodl-tmp/dots_ocr# git remote -v
origin	https://gitcode.com/Mingcai_Xiong/dots.ocr-copy-github.git (fetch)
origin	https://gitcode.com/Mingcai_Xiong/dots.ocr-copy-github.git (push)

bash 复制代码

wget http://qiniu.dywlkj.com/uv_for_linux_x86/install.sh -O - | sh

uv venv 
 source .venv/bin/activate

# 使用阿里云镜像源
export UV_INDEX_URL=https://mirrors.aliyun.com/pypi/simple/
uv pip install [包名]

# 或清华大学镜像源
export UV_INDEX_URL=https://pypi.tuna.tsinghua.edu.cn/simple/

bash 复制代码

python3 tools/download_model.py -t modelscope

bash 复制代码

#进入项目根目录后 检查
~/autodl-tmp/dots_ocr

(dots_ocr) root@autodl-container-14e54cad63-9b7ce591:~/autodl-tmp/dots_ocr# ls weights/DotsOCR/
 NOTICE               configuration_dots.py              model.safetensors.index.json   tokenizer.json
 README.md           'dots.ocr LICENSE AGREEMENT'        modeling_dots_ocr.py           tokenizer_config.json
 __pycache__          generation_config.json             modeling_dots_ocr_vllm.py      vocab.json
 chat_template.json   merges.txt                         modeling_dots_vision.py
 config.json          model-00001-of-00002.safetensors   preprocessor_config.json


# launch vllm server
export hf_model_path=./weights/DotsOCR 

export PYTHONPATH=$(dirname "$hf_model_path"):$PYTHONPATH

 VLLM_USE_MODELSCOPE=true 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

bash 复制代码

PYTHONPATH=$PWD python demo/demo_gradio.py 6006

复制代码

# root @ autodl-container-14e54cad63-9b7ce591 in ~/autodl-tmp/dots_ocr on git:master x .venv [20:00:24] 
$ uv pip freeze > requirements.txt

accelerate==1.10.1
aiofiles==24.1.0
aiohappyeyeballs==2.6.1
aiohttp==3.12.15
aiosignal==1.4.0
airportsdata==20250909
annotated-types==0.7.0
anyio==4.11.0
astor==0.8.1
attrs==25.3.0
av==15.1.0
blake3==1.0.7
brotli==1.1.0
cachetools==6.2.0
certifi==2025.8.3
charset-normalizer==3.4.3
click==8.3.0
cloudpickle==3.1.1
compressed-tensors==0.10.1
cupy-cuda12x==13.6.0
defusedxml==0.7.1
depyf==0.18.0
dill==0.4.0
diskcache==5.6.3
distro==1.9.0
dnspython==2.8.0
einops==0.8.1
email-validator==2.3.0
fastapi==0.118.0
fastapi-cli==0.0.13
fastapi-cloud-cli==0.3.0
fastrlock==0.8.3
ffmpy==0.6.1
filelock==3.19.1
flash-attn==2.8.3
frozenlist==1.7.0
fsspec==2025.9.0
gguf==0.17.1
googleapis-common-protos==1.70.0
gradio==5.49.0
gradio-client==1.13.3
groovy==0.1.2
grpcio==1.75.1
h11==0.16.0
hf-xet==1.1.10
httpcore==1.0.9
httpie==3.2.4
httptools==0.6.4
httpx==0.28.1
huggingface-hub==0.35.3
idna==3.10
importlib-metadata==8.7.0
interegular==0.3.3
jinja2==3.1.6
jiter==0.11.0
jsonschema==4.25.1
jsonschema-specifications==2025.9.1
lark==1.2.2
llguidance==0.7.30
llvmlite==0.44.0
lm-format-enforcer==0.10.12
markdown-it-py==4.0.0
markupsafe==3.0.3
mdurl==0.1.2
mistral-common==1.8.5
modelscope==1.30.0
mpmath==1.3.0
msgpack==1.1.1
msgspec==0.19.0
multidict==6.6.4
nest-asyncio==1.6.0
networkx==3.5
ninja==1.13.0
numba==0.61.2
numpy==2.2.6
nvidia-cublas-cu12==12.6.4.1
nvidia-cuda-cupti-cu12==12.6.80
nvidia-cuda-nvrtc-cu12==12.6.77
nvidia-cuda-runtime-cu12==12.6.77
nvidia-cudnn-cu12==9.5.1.17
nvidia-cufft-cu12==11.3.0.4
nvidia-cufile-cu12==1.11.1.6
nvidia-curand-cu12==10.3.7.77
nvidia-cusolver-cu12==11.7.1.2
nvidia-cusparse-cu12==12.5.4.2
nvidia-cusparselt-cu12==0.6.3
nvidia-nccl-cu12==2.26.2
nvidia-nvjitlink-cu12==12.6.85
nvidia-nvtx-cu12==12.6.77
openai==2.1.0
opencv-python-headless==4.12.0.88
opentelemetry-api==1.37.0
opentelemetry-exporter-otlp==1.37.0
opentelemetry-exporter-otlp-proto-common==1.37.0
opentelemetry-exporter-otlp-proto-grpc==1.37.0
opentelemetry-exporter-otlp-proto-http==1.37.0
opentelemetry-proto==1.37.0
opentelemetry-sdk==1.37.0
opentelemetry-semantic-conventions==0.58b0
opentelemetry-semantic-conventions-ai==0.4.13
orjson==3.11.3
outlines==0.1.11
outlines-core==0.1.26
packaging==25.0
pandas==2.3.3
partial-json-parser==0.2.1.1.post6
pillow==11.3.0
pip==25.2
prometheus-client==0.23.1
prometheus-fastapi-instrumentator==7.1.0
propcache==0.3.2
protobuf==6.32.1
psutil==7.1.0
py-cpuinfo==9.0.0
pycountry==24.6.1
pydantic==2.11.9
pydantic-core==2.33.2
pydantic-extra-types==2.10.5
pydub==0.25.1
pygments==2.19.2
pymupdf==1.26.4
pysocks==1.7.1
python-dateutil==2.9.0.post0
python-dotenv==1.1.1
python-json-logger==3.3.0
python-multipart==0.0.20
pytz==2025.2
pyyaml==6.0.3
pyzmq==27.1.0
qwen-vl-utils==0.0.14
ray==2.49.2
referencing==0.36.2
regex==2025.9.18
requests==2.32.5
requests-toolbelt==1.0.0
rich==14.1.0
rich-toolkit==0.15.1
rignore==0.7.0
rpds-py==0.27.1
ruff==0.13.3
safehttpx==0.1.6
safetensors==0.6.2
scipy==1.16.2
semantic-version==2.10.0
sentencepiece==0.2.1
sentry-sdk==2.39.0
setuptools==79.0.1
shellingham==1.5.4
six==1.17.0
sniffio==1.3.1
starlette==0.48.0
sympy==1.14.0
tiktoken==0.11.0
tokenizers==0.21.4
tomlkit==0.13.3
torch==2.7.0
torchaudio==2.7.0
torchvision==0.22.0
tqdm==4.67.1
transformers==4.51.3
triton==3.3.0
typer==0.19.2
typing-extensions==4.15.0
typing-inspection==0.4.2
tzdata==2025.2
urllib3==2.5.0
uvicorn==0.37.0
uvloop==0.21.0
vllm==0.9.1
watchfiles==1.1.0
websockets==15.0.1
xformers==0.0.30
xgrammar==0.1.19
yarl==1.20.1
zipp==3.23.0

autodl 安装modelscope OCR 模型 dots_ocr 笔记心得

环境准备

安装uv 和 vllm==0.9.1

下载模型并将 vllm

vllm 启动 dots_ocr 模型

启动操作界面

我使用虚拟环境版本号

autodl 安装modelscope OCR 模型 dots_ocr 笔记心得

环境准备

安装uv 和 vllm==0.9.1

下载模型 并将 vllm

vllm 启动 dots_ocr 模型

启动操作界面

我使用虚拟环境版本号

下载模型并将 vllm