Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.

★ 31,235⑂ 3,349👁 168⑃ 40● 75▤ 0
PythonMITCreated 2026-06-18
+28
日增长
+770
周增长
+4,177
月增长
31,235
stars
3,349
forks
168
watchers
40
prs
75
issues
0
releases

README

Unlimited OCR Works






  
    
  
  
    
  
  
    
  



  
    
  
    
    
  
  
    
  


Pioneering the OCR-3.0 Era: From Long- to Unlimited-Horizon Parsing.








 Release
- [2026/11/02] 📄 The paper of Unlimited OCR 2 is now available on arXiv.
- [2026/10/28] Thanks to the ms-swift community for supporting training of Unlimited OCR 2.
- [2026/10/27] 📊 We release MarathonDocBench, a new benchmark for ultra-long document parsing.
- [2026/10/27] 🤝 Thanks to the ModelScope community for their support. Our model is now available at ModelScope.
- [2026/10/27] 🤝 Thanks to the Baidu Cloud team for their support. Our model is now available on Baidu Cloud.
- [2026/10/27] 🤝 Thanks to AK for creating a new demo for us. Try it at Unlimited-OCR-2.
- [2026/10/27] 🚀 We release Unlimited OCR 2, achieving unlimited-horizon parsing with SR-SWA.
- [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.

 What's New in 2
 Sparse Reference Sliding Window Attention (SR-SWA): Compresses text-visual attention interactions from ultra-long sequences down to a fixed-size set of working references (e.g., 512 tokens). This bounds computational complexity, keeping per-step decoding latency and memory footprint nearly constant regardless of document length.
 From Long- to Unlimited-Horizon Parsing: Powered by SR-SWA, Unlimited-OCR 2 achieves true, unbounded document parsing within a finite context window—effectively eliminating quadratic attention scaling and memory bottlenecks as documents grow.
 Ultra-Long Document Parsing SOTA: Achieves state-of-the-art performance across both dozens-of-pages benchmarks (e.g., MPDocBench) and extreme hundred-page benchmarks (e.g., MarathonDocBench).


  


 Inference

 Unlimited OCR 2 supports Transformers (native, for quick tests) and SGLang (recommended for serving).

 Transformers

Tested with Python 3.10, torch==2.13.0, transformers==4.52.1, huggingface-hub==0.36.0, tokenizers==0.21.4, on an NVIDIA A800-80GB:
shell
pip install torch==2.13.0 torchvision pillow transformers==4.52.1 huggingface-hub==0.36.0 \
  tokenizers==0.21.4 addict==2.4.0 einops==0.8.2 easydict==1.13


Load the model once:
python
import torch
from transformers import AutoModel, AutoTokenizer

model_name = "baidu/Unlimited-OCR-2"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModel.f

Top issues

相关报道 (17)

note【毎朝のAI・テック要約】2026年11月2日 今日の注目ニュース3選2026-11-01PC Watch on MSNBaidu、数百ページの長文も高速OCRできる「Unlimited OCR 2」公開2026-10-29腾讯网百度开源文心Unlimited OCR 2,文档解析页数不再设限2026-10-28搜狐下载超 1000 万的模型上新!文心无限 OCR 干掉文档解析上限,3600 页一读到底2026-10-27新浪财经文档解析永动机!文心 Unlimited OCR 2 杀疯了,一口气读完三体全集2026-10-27搜狐Unlimited OCR 续作来袭:文档解析永动机 , 彻底告别页数限制2026-10-27techritual百度開源 Unlimited-OCR:33 億參數本機跑,一次過讀晒多頁文件2026-08-09moomooKimi K3、Unlimited OCR包攬全球前二,中國開源模型持續刷屏海外2026-08-08腾讯网5天GitHub Star破万!百度Unlimited OCR引爆股价,百度港股涨超 8%2026-06-29capitalfutures百度推出Unlimited OCR模型並在多個平台登頂2026-06-28
展开其余 7 条電腦王阿達百度推出開源 OCR 模型 Unlimited-OCR,3B 參數碾壓 GPT-5 級模型2026-06-25品玩OCR 3.0 时代来了!文心 Unlimited OCR 2 开源发布,超长文档解析迎来“页数自由”2026-10-27半月谈Kimi K3、Unlimited OCR包揽全球前二,中国开源模型持续刷屏海外2026-07-28CSDN博客HuggingFace、GitHub四榜第一!百度 Unlimited OCR 开源 5 天 Star 破万,引爆全球A2026-06-29雪球5天GitHub Star破万!百度Unlimited OCR引爆全球技术圈,跻身开源“现象级爆款”2026-06-26智源社区刚刚,百度开源拿下全球第一!作者疑似DeepSeek出走大神2026-06-23www.80aj.com百度推出Unlimited-OCR:基于DeepSeek架构的长文档解析开源模型2026-06-23

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON