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().
text + image → text · made by Baidu
Sold by
Nobody in the catalogue publishes a price for this yet.
About
Unlimited-OCR — a text model from Baidu.
It takes text and images and returns text. It was published in June 2026. The catalogue files it under ocr. Its weights are published under MIT, so you may run it on your own machine, or buy it from whoever serves it cheapest.
Every current figure
- Maker
- Baidu
- Register
- model
- Takes
- text + image
- Returns
- text
- Published
- June 2026
- Parameters
- 3.3 billion · read from its own weights
- Licence
- mit
Known as 1 name
baidu/Unlimited-OCR