单图问答（MiniCPM-V 4.7）

MiniCPM-V 4.7 已在 transformers >= 5.18.0 中注册为独立架构 MiniCPMV4_7ForConditionalGeneration，标准 HuggingFace Processor + model.generate 流程即可使用，无需 trust_remote_code。

4.7 有两个尺寸，改 model_path 即可切换：

`model_path`	尺寸
`openbmb/MiniCPM-V-4.7-1B`	dense 1B（端侧）
`openbmb/MiniCPM-V-4.7-35B-A3B`	MoE 35B-A3B（高吞吐）

初始化模型

import torch
from PIL import Image
from transformers import AutoProcessor, AutoModelForImageTextToText

model_path = "openbmb/MiniCPM-V-4.7-1B"   # 或 "openbmb/MiniCPM-V-4.7-35B-A3B"

processor = AutoProcessor.from_pretrained(model_path)
model = AutoModelForImageTextToText.from_pretrained(
    model_path,
    dtype="auto",
    device_map="auto",
    attn_implementation="sdpa",  # 或 "flash_attention_2"
).eval()

单图对话

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

# 第一轮
question = "图中是什么地貌？"
messages = [{
    "role": "user",
    "content": [
        {"type": "image", "image": image},
        {"type": "text", "text": question},
    ],
}]

inputs = processor.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
    chat_template_kwargs={"enable_thinking": False},
).to(model.device)

out_ids = model.generate(**inputs, max_new_tokens=512)
answer = processor.decode(
    out_ids[0][inputs["input_ids"].shape[-1]:],
    skip_special_tokens=True,
)
print(answer)

第二轮

messages.append({"role": "assistant", "content": [{"type": "text", "text": answer}]})
messages.append({
    "role": "user",
    "content": [{"type": "text", "text": "去这里旅行需要注意什么？"}],
})

inputs = processor.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
    chat_template_kwargs={"enable_thinking": False},
).to(model.device)

out_ids = model.generate(**inputs, max_new_tokens=512)
answer = processor.decode(
    out_ids[0][inputs["input_ids"].shape[-1]:],
    skip_special_tokens=True,
)
print(answer)

示例图片

alt text

思考模式说明

4.7 每个尺寸只有一个 checkpoint：对话模板默认带 <think> 块，除非传入 chat_template_kwargs={"enable_thinking": False}。重 OCR / 推理类任务可保留思考；普通问答建议关闭以获得更快的直答。