Unlimited OCR 2
Image text to text model by baidu
Unlimited OCR 2 launched on 26 October 2026. It ranked #19 on Daily Launch on 30 October 2026 with a Launch Score of 61, from trending score 386 on Hugging Face. It moved up 17 places from the day before.
What is Unlimited OCR 2?
The prompt is built automatically as " " numpages + "Multi page parsing.", and each page is encoded as one global view (base mode). The output contains one per input page, in the same order as imagefiles. Notes on the knobs that matter for memory: --mem-fraction-static is the share reserved for weights + KV. The largest --cuda-graph-bs-prefill bucket must equal --max-prefill-tokens.
From its model card on Hugging Face
Unlimited OCR 2 is a model by baidu on Hugging Face. It is released under the MIT license.
How to get Unlimited OCR 2
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==1.13From its model card on Hugging Face
More steps and the source are in its model card on Hugging Face.