手机端可运行的GPT-4V级别多模态大模型：支持单图、多图与视频理解

from PIL import Image
import torch
from transformers import AutoModel, AutoTokenizer

model_path = 'openbmb/MiniCPM-V-4'
model = AutoModel.from_pretrained(model_path, trust_remote_code=True,
                                  # sdpa or flash_attention_2, no eager
                                  attn_implementation='sdpa', torch_dtype=torch.bfloat16)
model = model.eval().cuda()
tokenizer = AutoTokenizer.from_pretrained(
    model_path, trust_remote_code=True)



image = Image.open('./assets/single.png').convert('RGB')

# First round chat 
question = "What is the landform in the picture?"
msgs = [{'role': 'user', 'content': [image, question]}]

answer = model.chat(
    msgs=msgs,
    image=image,
    tokenizer=tokenizer
)
print(answer)


# Second round chat, pass history context of multi-turn conversation
msgs.append({"role": "assistant", "content": [answer]})
msgs.append({"role": "user", "content": [
            "What should I pay attention to when traveling here?"]})

answer = model.chat(
    msgs=msgs,
    image=None,
    tokenizer=tokenizer
)
print(answer)

@article{yao2024minicpm,
  title={MiniCPM-V: A GPT-4V Level MLLM on Your Phone},
  author={Yao, Yuan and Yu, Tianyu and Zhang, Ao and Wang, Chongyi and Cui, Junbo and Zhu, Hongji and Cai, Tianchi and Li, Haoyu and Zhao, Weilin and He, Zhihui and others},
  journal={Nat Commun 16, 5509 (2025)},
  year={2025}
}