Name: Unlimited OCR
Author: baidu

简介

Unlimited OCR 是由百度推出的一款开源图像文本识别模型，旨在解决复杂场景下的文字提取痛点。不同于传统的 OCR 工具，它在处理非结构化排版、多语言混排以及低质量图像时具有更强的鲁棒性。对于开发者而言，由于采用了 MIT 许可，该模型非常适合集成到企业内部的文档数字化流程或自动化办公插件中。其上手门槛较低，能够快速将图片、扫描件转化为可编辑的文本，是构建 RAG（检索增强生成）知识库时高效处理 PDF 和图片数据的理想预处理组件。

核心亮点

MIT 开源协议，企业级部署无版权压力
精准识别复杂排版，支持多语言混合提取
极低上手难度，快速集成至自动化工作流
高效处理扫描件，为 RAG 知识库提供纯净文本

使用方法

安装依赖

# 安装 Hugging Face transformers
pip install transformers torch

SDK 使用

# 使用 transformers 加载模型
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("baidu/Unlimited-OCR")
tokenizer = AutoTokenizer.from_pretrained("baidu/Unlimited-OCR")

Hugging Face 下载

我们推荐使用命令行或者 Hugging Face Hub SDK 来进行模型的下载。

操作指引：在下载前，请先通过如下命令安装 huggingface_hub：

操作指引

pip install -U huggingface_hub

命令行下载

下载完整模型库

huggingface-cli download baidu/Unlimited-OCR

下载单个文件到指定本地文件夹（以下载 config.json 到当前路径下 ./dir 目录为例）

huggingface-cli download baidu/Unlimited-OCR config.json --local-dir ./dir

更多命令行下载选项，可参见官方文档

SDK 下载

# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('baidu/Unlimited-OCR')

Git 下载

请确保 lfs 已经被正确安装

Git 下载

git lfs install
git clone https://huggingface.co/baidu/Unlimited-OCR

如果您希望跳过 lfs 大文件下载，可以使用如下命令

跳过 LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/baidu/Unlimited-OCR

模型文件托管在 Hugging Face Hub，使用 HF CLI / SDK / Git 直接下载，不经过本站。

PyTorch / Transformers 使用

安装 Transformers

pip install -U transformers torch

模型加载和推理

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('baidu/Unlimited-OCR')
tokenizer = AutoTokenizer.from_pretrained('baidu/Unlimited-OCR')

完整文档

来源: HuggingFace

---
pipeline_tag: image-text-to-text
language:

multilingual

tags:

baidu

vision-language

ocr

custom_code

license: mit
library_name: transformers
---
<p align="center">
<img src="assets/baidu.png" width="55%" alt="Baidu Inc." />
</p>

<hr>

<h1 align="center">Unlimited OCR Works</h1>

<h3 align="center">Welcome the Era of One-shot Long-horizon Parsing.</h3>

Release

[2026/07/21] 🤝 Thanks to the ms-swift community for their support, our model now supports training with ms-swift.

[2026/07/03] 🤝 Thanks to the Baidu Cloud team for their support. Our model is now available on Baidu Cloud.

[2026/06/28] 🤝 Thanks to the vLLM community and Tianyu Guo for their support, our model now supports vLLM inference.

[2026/06/24] 🤝 Thanks to AK for creating a demo for us. It is now available at Hugging Face Spaces.

[2026/06/23] 📄 Our paper is now available on arXiv.

[2026/06/23] 🤝 Thanks to the ModelScope community for their support. Our model is now available at ModelScope.

[2026/06/22] 🚀 We present Unlimited-OCR, aiming to push Deepseek-OCR one step further.

Inference

Transformers

Inference using Huggingface transformers on NVIDIA GPUs. Requirements tested on python 3.12.3 + CUDA12.9：

code

torch==2.10.0
torchvision==0.25.0
transformers==4.57.1
Pillow==12.1.1
matplotlib==3.10.8
einops==0.8.2
addict==2.4.0
easydict==1.13
pymupdf==1.27.2.2
psutil==7.2.2

python

import os
import torch
from transformers import AutoModel, AutoTokenizer
model_name = 'baidu/Unlimited-OCR'
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModel.from_pretrained(
    model_name,
    trust_remote_code=True,
    use_safetensors=True,
    torch_dtype=torch.bfloat16,
)
model = model.eval().cuda()
── Single image supports two configs: gundam or base ──
gundam: base_size=1024, image_size=640, crop_mode=True
base: base_size=1024, image_size=1024, crop_mode=False
model.infer(
    tokenizer,
    prompt='<image>document parsing.',
    image_file='your_image.jpg',
    output_path='your/output/dir',
    base_size=1024, image_size=640, crop_mode=True,
    max_length=32768,
    no_repeat_ngram_size=35, ngram_window=128,
    save_results=True,
)
── Multi page / PDF only uses base (image_size=1024) ──
model.infer_multi(
    tokenizer,
    prompt='<image>Multi page parsing.',
    image_files=['page1.png', 'page2.png', 'page3.png'],
    output_path='your/output/dir',
    image_size=1024,
    max_length=32768,
    no_repeat_ngram_size=35, ngram_window=1024,
    save_results=True,
)
── PDF (convert pages to images, then multi-page parsing) ──
import tempfile, fitz  # PyMuPDF
def pdf_to_images(pdf_path, dpi=300):
    doc = fitz.open(pdf_path)
    tmp_dir = tempfile.mkdtemp(prefix='pdf_ocr_')
    mat = fitz.Matrix(dpi / 72, dpi / 72)
    paths = []
    for i, page in enumerate(doc):
        out = os.path.join(tmp_dir, f'page_{i+1:04d}.png')
        page.get_pixmap(matrix=mat).save(out)
        paths.append(out)
    doc.close()
    return paths
model.infer_multi(
    tokenizer,
    prompt='<image>Multi page parsing.',
    image_files=pdf_to_images('your_doc.pdf', dpi=300),
    output_path='your/output/dir',
    image_size=1024,
    max_length=32768,
    no_repeat_ngram_size=35, ngram_window=1024,
    save_results=True,
)

vLLM

Please refer to the official vLLM recipe for deployment details:

Recipe: https://recipes.vllm.ai/baidu/Unlimited-OCR

##### Docker Images
Use the following Docker images depending on your GPU platform:

Default (CUDA 13.0):

bash

docker pull vllm/vllm-openai:unlimited-ocr

For Hopper GPUs (CUDA 12.9)

bash

docker pull vllm/vllm-openai:unlimited-ocr-cu129

SGLang

Set up the environment (uv-managed virtualenv). Install the local SGLang wheel first,
then pin kernels==0.9.0 and install PyMuPDF for PDF-to-image conversion:

shell

uv venv --python 3.12 source .venv/bin/activate

uv pip install wheel/sglang-0.0.0.dev11416+g92e8bb79e-py3-none-any.whl uv pip install kernels==0.11.7 uv pip install pymupdf==1.27.2.2

Start the SGLang server:

shell

python -m sglang.launch_server \
    --model baidu/Unlimited-OCR \
    --served-model-name Unlimited-OCR \
    --attention-backend fa3 \
    --page-size 1 \
    --mem-fraction-static 0.8 \
    --context-length 32768 \
    --enable-custom-logit-processor \
    --disable-overlap-schedule \
    --skip-server-warmup \
    --host 0.0.0.0 \
    --port 10000

Send streaming requests to the OpenAI-compatible API:
```python
import base64
import json
import os
import tempfile

import fitz
import requests
from sglang.srt.sampling.custom_logit_processor import DeepseekOCRNoRepeatNGramLogitProcessor

server_url = "http://127.0.0.1:10000"

session = requests.Session()
session.trust_env = False

def pdf_to_images(pdf_path, dpi=300):
doc = fitz.open(pdf_path)
tmp_dir = tempfile.mkdtemp(prefix="pdf_ocr_")
mat = fitz.Matrix(dpi / 72, dpi / 72)
image_paths = []
for i, page in enumerate(doc):
image_path = os.path.join(tmp_dir, f"page_{i + 1:04d}.png")
page.get_pixmap(matrix=mat).save(image_path)
image_paths.append(image_path)
doc.close()
return image_paths

def encode_image(image_path):
ext = os.path.splitext(image_path)[1].lower()
mime = "image/jpeg" if ext in (".jpg", ".jpeg") else f"image/{ext.lstrip('.')}"
with open(image_path, "rb") as f:
data = base64.b64encode(f.read()).decode("utf-8")
return {"type": "image_url", "image_url": {"url": f"data:{mime};base64,{data}"}}

def build_content(prompt, image_paths):
return [{"type": "text", "text": prompt}] + [encode_image(path) for path in image_paths]

def generate(prompt, image_paths, image_mode, ngram_window):
payload = {
"model": "Unlimited-OCR",
"messages": [{"role": "user", "content": build_content(prompt, image_paths)}],
"temperature": 0,
"skip_special_tokens": False,
"images_config": {"image_mode": image_mode},
"custom_logit_processor": DeepseekOCRNoRepeatNGramLogitProcessor.to_str(),
"custom_params": {
"ngram_size": 35,
"window_size": ngram_window,
},
"s

Unlimited OCR

简介

核心亮点

使用方法

Hugging Face 下载

命令行下载

SDK 下载

Git 下载

PyTorch / Transformers 使用

完整文档

Release

Inference

Transformers

── Single image supports two configs: gundam or base ──

gundam: base_size=1024, image_size=640, crop_mode=True

base: base_size=1024, image_size=1024, crop_mode=False

── Multi page / PDF only uses base (image_size=1024) ──

── PDF (convert pages to images, then multi-page parsing) ──

vLLM

SGLang

扫码进交流群