pip install transformers==4.57.1 accelerate

from transformers import Qwen3VLForConditionalGeneration, AutoProcessor

model = Qwen3VLForConditionalGeneration.from_pretrained(
    "inclusionAI/ArmorOCR", dtype="auto", device_map="auto",
)
processor = AutoProcessor.from_pretrained("inclusionAI/ArmorOCR")

messages = [{
    "role": "user",
    "content": [
        {"type": "image", "image": "path/to/image.png"},
        {"type": "text",
         "text": ("Please identify the text in the image. "
                  "Put your reasoning inside <analyze></analyze> "
                  "and your final recognized text inside <answer></answer>.")},
    ],
}]

inputs = processor.apply_chat_template(
    messages, tokenize=True, add_generation_prompt=True,
    return_dict=True, return_tensors="pt",
).to(model.device)

out = model.generate(**inputs, max_new_tokens=256)
trimmed = [o[len(i):] for i, o in zip(inputs.input_ids, out)]
print(processor.batch_decode(trimmed, skip_special_tokens=True))

@misc{cao2026armorocrgroundedadversarialvisual,
      title={ArmorOCR: Grounded Adversarial Visual Perception via Observation-Transferred Self-Distillation}, 
      author={Linhan Cao and Siyuan Li and Jun Lan and Liangbo He and Guannan Li and Xiaolei Huang and Jun Jia and Shuheng Zhou and Huijia Zhu and Weiqiang Wang and Wei Sun},
      year={2026},
      eprint={2608.20122},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2608.20122}, 
}