Instructions to use baidu/Unlimited-OCR-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use baidu/Unlimited-OCR-2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="baidu/Unlimited-OCR-2", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("baidu/Unlimited-OCR-2", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use baidu/Unlimited-OCR-2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "baidu/Unlimited-OCR-2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "baidu/Unlimited-OCR-2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/baidu/Unlimited-OCR-2
- SGLang
How to use baidu/Unlimited-OCR-2 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "baidu/Unlimited-OCR-2" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "baidu/Unlimited-OCR-2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "baidu/Unlimited-OCR-2" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "baidu/Unlimited-OCR-2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use baidu/Unlimited-OCR-2 with Docker Model Runner:
docker model run hf.co/baidu/Unlimited-OCR-2
Turkish
More than 200 million people in the world speak Turkish
Thank you very much for your suggestion! Expanding language coverage is firmly on our roadmap — future releases will support a broader range of languages, and Turkish will definitely be among them.Thanks again for trying UOW2 and for taking the time to share your feedback — it really helps us prioritize what to improve next.
Thank you for your excellent work
More than 200 million people in the world speak Turkish
thats true and we are one of them, model developers always refuse to add turkish to new models
Top 15 Languages by Total Speakers (2026)
Rank Language First-Language (L1) Second-Language (L2) Total Speakers
1 English 372M 1,121M 1.49B
2 Mandarin Chinese 988M 194M 1.18B
3 Hindi 347M 264M 611M
4 Spanish 487M 75M 561M
5 Modern Standard Arabic 0 335M 335M
6 French 75M 258M 334M
7 Bengali 234M 43M 274M
8 Portuguese 252M 18M 269M
9 Indonesian 78M 177M 255M
10 Urdu 78M 168M 246M
11 Russian 133M 77M 210M
12 Standard German 76M 57M 133M
13 Japanese 124M 2M 126M
14 Nigerian Pidgin 5M 116M 121M
15 Egyptian Arabic 83M 35M 118M
Turkish Speaker Breakdown (2026)
• Total Speakers: 94 million
• First-Language (L1) Native Speakers: 86 million
• Second-Language (L2) Speakers: 7 million
just saying...
Top 15 Languages by Total Speakers (2026)
Rank Language First-Language (L1) Second-Language (L2) Total Speakers
1 English 372M 1,121M 1.49B
2 Mandarin Chinese 988M 194M 1.18B
3 Hindi 347M 264M 611M
4 Spanish 487M 75M 561M
5 Modern Standard Arabic 0 335M 335M
6 French 75M 258M 334M
7 Bengali 234M 43M 274M
8 Portuguese 252M 18M 269M
9 Indonesian 78M 177M 255M
10 Urdu 78M 168M 246M
11 Russian 133M 77M 210M
12 Standard German 76M 57M 133M
13 Japanese 124M 2M 126M
14 Nigerian Pidgin 5M 116M 121M
15 Egyptian Arabic 83M 35M 118MTurkish Speaker Breakdown (2026)
• Total Speakers: 94 million
• First-Language (L1) Native Speakers: 86 million
• Second-Language (L2) Speakers: 7 millionjust saying...
that may be true but it feels so bad that everyone ignores us