baidu/Unlimited-OCR

Name: baidu/Unlimited-OCR
Creator: baidu
License: mit

image-text-to-texttransformersVerified checksumsbaiduvision-languageocrcustom_codetransformerssafetensors

License: mit
Size: 6.3 GB
Revision: main
Downloads in the last 30 days: 0 / 30 days

Mirrored from baidu/Unlimited-OCR

All models by baidu →

[Image blocked: Baidu Inc.]

Unlimited OCR Works

Welcome the Era of One-shot Long-horizon Parsing.

[Image blocked: Unlimited OCR overview]

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：

python

import osimport torchfrom 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=Falsemodel.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):

For Hopper GPUs (CUDA 12.9)

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:

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 base64import jsonimport osimport tempfile
import fitzimport requestsfrom 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,        },        "stream": True,    }    response = session.post(        f"{server_url}/v1/chat/completions",        headers={"Content-Type": "application/json"},        data=json.dumps(payload),        timeout=1200,        stream=True,    )    response.raise_for_status()
    chunks = []    for line in response.iter_lines(chunk_size=1, decode_unicode=True):        if not line or not line.startswith("data: "):            continue        data = line[len("data: "):]        if data == "[DONE]":            break        event = json.loads(data)        delta = event["choices"][0].get("delta", {}).get("content", "")        if delta:            print(delta, end="", flush=True)            chunks.append(delta)    print()    return "".join(chunks)

# Single image supports two configs: gundam or base. Example below uses gundam.generate("document parsing.", ["your_image.jpg"], image_mode="gundam", ngram_window=128)
# Multi image (base only)generate("Multi page parsing.", ["page1.png", "page2.png"], image_mode="base", ngram_window=1024)
# PDF (base only)generate("Multi page parsing.", pdf_to_images("your_doc.pdf", dpi=300), image_mode="base", ngram_window=1024)

For OmniDocBench evaluation, you need to perform the following post-processing.

python

DET_RE = re.compile(r'<\|det\|>([^<\s]+)(?:\s*\[[^\]]*\])?\s*<\|/det\|>(.*)', re.DOTALL)
def remove_det(raw: str) -> str:    """    Strip <|det|>type [bbox]<|/det|> markers, group lines belonging to the    same block with \\n, and separate different blocks with \\n\\n.    """    blocks = []    cur = None    for line in raw.splitlines():        line = line.rstrip()        if not line:            continue        m = DET_RE.match(line)        if m:            category, content = m.group(1).strip(), m.group(2).strip()            if category == 'image':                continue            if cur is not None:                blocks.append(cur)            cur = [content] if content else []            continue        if cur is None:            cur = []        cur.append(line)    if cur is not None:        blocks.append(cur)    text = '\n\n'.join('\n'.join(b) for b in blocks).strip()    return text

Visualization

[Image blocked: Long-horizon OCR demo]

Acknowledgement

We would like to thank Deepseek-OCR, Deepseek-OCR-2, PaddleOCR for their valuable models and ideas.

Citation

bibtex

@misc{yin2026unlimitedocrworks,      title={Unlimited OCR Works},       author={Youyang Yin and Huanhuan Liu and YY and Qunyi Xie and Chaorun Liu and Shiqi Yang and Shaohua Wang and Zhanlong Liu and Hao Zou and Jinyue Chen and Shu Wei and Jingjing Wu and Mingxin Huang and Zhen Wu and Guibin Wang and Tengyu Du and Lei Jia},      year={2026},      eprint={2606.23050},      archivePrefix={arXiv},      primaryClass={cs.CV},      url={https://arxiv.org/abs/2606.23050}, }