Instructions to use openbmb/MiniCPM4-Survey with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openbmb/MiniCPM4-Survey with Transformers:

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

pipe = pipeline("text-generation", model="openbmb/MiniCPM4-Survey", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("openbmb/MiniCPM4-Survey", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use openbmb/MiniCPM4-Survey with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openbmb/MiniCPM4-Survey"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openbmb/MiniCPM4-Survey",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openbmb/MiniCPM4-Survey

SGLang

How to use openbmb/MiniCPM4-Survey 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 "openbmb/MiniCPM4-Survey" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openbmb/MiniCPM4-Survey",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "openbmb/MiniCPM4-Survey" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openbmb/MiniCPM4-Survey",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openbmb/MiniCPM4-Survey with Docker Model Runner:
```
docker model run hf.co/openbmb/MiniCPM4-Survey
```

BigDong

Jeol commited on Jun 25, 2025

Commit

adfe3fb

verified ·

1 Parent(s): 08c3956

fix typo (#2)

Browse files

- fix typo (726d83d1d2c1937a944f71b4c83d32ce86cf04dc)

Co-authored-by: Bing <Jeol@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -60,7 +60,7 @@ Key features include:
 Download [MiniCPM4-Survey](https://huggingface.co/openbmb/MiniCPM4-Survey) from Hugging Face and place it in `model/MiniCPM4-Survey`.
 We recommend using [MiniCPM-Embedding-Light](https://huggingface.co/openbmb/MiniCPM-Embedding-Light) as the embedding model, which can be downloaded from Hugging Face and placed in `model/MiniCPM-Embedding-Light`.
-### Perpare the environment
 You can download the [paper data](https://www.kaggle.com/datasets/Cornell-University/arxiv) from Kaggle, then extract it. You can run `python data_process.py` to process the data and generate the retrieval database. Then you can run `python build_index.py` to build the retrieval database.

 Download [MiniCPM4-Survey](https://huggingface.co/openbmb/MiniCPM4-Survey) from Hugging Face and place it in `model/MiniCPM4-Survey`.
 We recommend using [MiniCPM-Embedding-Light](https://huggingface.co/openbmb/MiniCPM-Embedding-Light) as the embedding model, which can be downloaded from Hugging Face and placed in `model/MiniCPM-Embedding-Light`.
+### Prepare the environment
 You can download the [paper data](https://www.kaggle.com/datasets/Cornell-University/arxiv) from Kaggle, then extract it. You can run `python data_process.py` to process the data and generate the retrieval database. Then you can run `python build_index.py` to build the retrieval database.