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))