Qwen能吞下整本扫描版PDF，直接转Word了，这波操作太赞了！

nvidia-smi --list-gpus

pip install torch torchvision --index-url https://download.pytorch.org/whl/cu121pip install transformers safetensors

pip install opencv-python

pip install accelerate

from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessorfrom qwen_vl_utils import process_vision_info# default: Load the model on the available device(s)model = Qwen2_5_VLForConditionalGeneration.from_pretrained(    "Qwen/Qwen2.5-VL-7B-Instruct", torch_dtype="auto", device_map="auto")# We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.# model = Qwen2_5_VLForConditionalGeneration.from_pretrained(#     "Qwen/Qwen2.5-VL-7B-Instruct",#     torch_dtype=torch.bfloat16,#     attn_implementation="flash_attention_2",#     device_map="auto",# )# default processerprocessor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct")# The default range for the number of visual tokens per image in the model is 4-16384.# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.# min_pixels = 256*28*28# max_pixels = 1280*28*28# processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels)messages = [    {        "role": "user",        "content": [            {                "type": "image",                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",            },            {"type": "text", "text": "请用中文描述这张图片的内容。"},        ],    }]# Preparation for inferencetext = processor.apply_chat_template(    messages, tokenize=False, add_generation_prompt=True)image_inputs, video_inputs = process_vision_info(messages)inputs = processor(    text=[text],    images=image_inputs,    videos=video_inputs,    padding=True,    return_tensors="pt",)inputs = inputs.to("cuda")# Inference: Generation of the outputgenerated_ids = model.generate(**inputs, max_new_tokens=128)generated_ids_trimmed = [    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]output_text = processor.batch_decode(    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)print(output_text)

scp -P 41277 ocr_test.pdf root@你的服务器名字（来源文章一开始复制的登录地址）

pip install pdf2image python-docx

sudo apt updatesudo apt install poppler-utils