yang1232009/HanMoVLM

import os
import torch

from transformers import AutoModelForVision2Seq, AutoProcessor
from peft import PeftModel
from qwen_vl_utils import process_vision_info


MODEL_PATH = "Qwen/Qwen3-VL-8B-Instruct"
ADAPTER_PATH = "yang1232009/HanMoVLM"
IMAGE_PATH = ""

PROMPT_TEXT = (
    "<image>你是一位中国传统绘画鉴赏专家，熟悉笔墨技法、中国画美学、艺术史与文人画理论。"
    "请对输入的国风绘画图像进行深入、专业、客观以及细致的艺术评估。\n"
    "按以下格式输出：\n"
    "原因分析: [详细分析]\n"
    "最终分数: [0-5整数分数]"
)



base_model = AutoModelForVision2Seq.from_pretrained(
        MODEL_PATH,
        torch_dtype=torch.float16,
        device_map="cuda",
    )


model = PeftModel.from_pretrained(base_model, ADAPTER_PATH)
model = model.merge_and_unload()
model.eval()

processor = AutoProcessor.from_pretrained(MODEL_PATH)


image_path = IMAGE_PATH
if not os.path.exists(image_path):
    raise FileNotFoundError(f"Image file not found: {image_path}")
    

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": image_path},
            {"type": "text", "text": PROMPT_TEXT},
        ],
    }
]

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

# Inference: Generation of the output
generated_ids = model.generate(**inputs, max_new_tokens=4096)
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)