Instructions to use rty813/MiniCPM-V-4.7-1B-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rty813/MiniCPM-V-4.7-1B-bf16 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="rty813/MiniCPM-V-4.7-1B-bf16")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("rty813/MiniCPM-V-4.7-1B-bf16")
model = AutoModelForMultimodalLM.from_pretrained("rty813/MiniCPM-V-4.7-1B-bf16", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rty813/MiniCPM-V-4.7-1B-bf16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rty813/MiniCPM-V-4.7-1B-bf16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rty813/MiniCPM-V-4.7-1B-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/rty813/MiniCPM-V-4.7-1B-bf16

SGLang

How to use rty813/MiniCPM-V-4.7-1B-bf16 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "rty813/MiniCPM-V-4.7-1B-bf16" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rty813/MiniCPM-V-4.7-1B-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "rty813/MiniCPM-V-4.7-1B-bf16" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rty813/MiniCPM-V-4.7-1B-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use rty813/MiniCPM-V-4.7-1B-bf16 with Docker Model Runner:
```
docker model run hf.co/rty813/MiniCPM-V-4.7-1B-bf16
```

MiniCPM-V-4.7-1B-bf16 (bf16)

Full-precision (bf16) PyTorch port of openbmb/MiniCPM-V-4.7-1B, for vLLM / TGI / Xinference / transformers users who don't want the GGUF quant.

Format: pytorch_model.bin (bf16). safetensors conversion in progress.
Architecture: identical to the original — drop-in for AutoModelForCausalLM.from_pretrained("rty813/MiniCPM-V-4.7-1B-bf16").
Also loads in vLLM (vllm serve rty813/MiniCPM-V-4.7-1B-bf16) and Xinference (search "MiniCPM-V-4.7-1B").

Original model card:

license: apache-2.0 pipeline_tag: image-text-to-text tags: - minicpm-v - multimodal - On-Device Model - lightweight library_name: transformers

MiniCPM-V 4.7

GitHub · Evaluation · Examples · Usage · Model weights

MiniCPM-V 4.7 is the latest model in the MiniCPM-V series, available in a 1B variant. It builds on the family's single-image, multi-image, and video understanding capabilities, combining stronger foundation capabilities with efficient visual encoding and on-device inference. Notable features of MiniCPM-V 4.7 include:

🔥 A New Pareto Frontier in Performance and Efficiency. As model capabilities continue to advance, inference efficiency has become an important measure of a model's value. On resource-constrained devices, delivering the strongest possible capabilities within a limited resource budget calls for higher capability density. The 1B variant of MiniCPM-V 4.7 advances the performance–efficiency Pareto frontier for MLLMs. In Instruct mode, the 1B variant continues to improve foundation capabilities over MiniCPM-V 4.6 and substantially outperforms Qwen3.5 0.8B in both overall score and inference efficiency.
🚀 Efficient Architecture. Based on the intra-ViT early compression technique from LLaVA-UHD v4, MiniCPM-V 4.7 compresses visual tokens early within the vision encoder, reducing

Downloads last month: 67

Model tree for rty813/MiniCPM-V-4.7-1B-bf16

Base model

openbmb/MiniCPM-V-4.7-1B

Finetuned

(7)

this model