Single Image (MiniCPM-V 4.7)

MiniCPM-V 4.7 is registered upstream in transformers >= 5.18.0 as the standalone architecture MiniCPMV4_7ForConditionalGeneration, so the standard HuggingFace Processor + model.generate flow works out of the box — no trust_remote_code needed.

MiniCPM-V 4.7 comes in two sizes; swap model_path to pick one:

`model_path`	Size
`openbmb/MiniCPM-V-4.7-1B`	dense 1B (edge)
`openbmb/MiniCPM-V-4.7-35B-A3B`	MoE 35B-A3B (high-throughput)

Initialize model

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

model_path = "openbmb/MiniCPM-V-4.7-1B"   # or "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",  # or "flash_attention_2"
).eval()

Chat with a single image

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

# First round
question = "What is the landform in the picture?"
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)

Second round

messages.append({"role": "assistant", "content": [{"type": "text", "text": answer}]})
messages.append({
    "role": "user",
    "content": [{"type": "text", "text": "What should I pay attention to when traveling here?"}],
})

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)

Sample image

alt text

Notes on thinking

4.7 is a single checkpoint per size: the chat template emits a <think> block unless you pass chat_template_kwargs={"enable_thinking": False}. Leave thinking on for hard OCR / reasoning tasks; turn it off for snappy plain replies.