from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info
MODEL_PATH = "Qwen/Qwen2.5-VL-7B-Instruct-AWQ"
model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    MODEL_PATH,
    device_map="auto"
)
processor = AutoProcessor.from_pretrained(MODEL_PATH)

messages = [{
    "role": "user",
    "content": [
        {"type": "image", "image": "https://raw.githubusercontent.com/ymcui/Chinese-LLaMA-Alpaca-3/refs/heads/main/pics/banner.png"},
        {"type": "text", "text": "请你描述一下这张图片。"},
    ],
}]

text = 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",
).to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=512)
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[0])