Instructions to use openbmb/MiniCPM5-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openbmb/MiniCPM5-2B with Transformers:

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

pipe = pipeline("text-generation", model="openbmb/MiniCPM5-2B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openbmb/MiniCPM5-2B")
model = AutoModelForCausalLM.from_pretrained("openbmb/MiniCPM5-2B", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use openbmb/MiniCPM5-2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openbmb/MiniCPM5-2B"
# 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/MiniCPM5-2B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openbmb/MiniCPM5-2B

SGLang

How to use openbmb/MiniCPM5-2B 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/MiniCPM5-2B" \
    --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/MiniCPM5-2B",
		"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/MiniCPM5-2B" \
        --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/MiniCPM5-2B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openbmb/MiniCPM5-2B with Docker Model Runner:
```
docker model run hf.co/openbmb/MiniCPM5-2B
```

MiniCPM5-2B

Commit History

Sep 21 29 days ago

03:43
Remove the dead `<tool_sep>` branch from chat_template.jinja (fixes OpenBMB/MiniCPM#379)⁠

lhz7891444

Verified signature
930f638

Sep 12

07:20
Enhance README with sampling parameter recommendations and Llama.cpp usage examples

funmaker

12a3808
04:12
Enhance README with sampling parameter recommendations and Llama.cpp usage examples

funmaker

62b9b3b

Sep 10

09:36
Add a LiteRT-LM row to the Deployment cookbook table

funmaker

abe115e
09:08
Add a LiteRT-LM row to the Deployment cookbook table (#12)⁠

funmaker +1: mlboydaisuke

bca2410

Sep 9

07:48
docs: update README

funmaker

cd199ce
07:27
add `MiniCPM5-2B-DSpark-GGUF`

funmaker

d6c082b

Sep 8

09:08
add the LiteRT-LM version of MiniCPM5-2B

funmaker

a063f08
03:57
docs: update links of `Just RL II` and formatting in README files for clarity and consistency

funmaker

0e9c66d

Sep 7

07:20
update README

funmaker

3497c46
03:24
update README

BigDong

d3ad48d
03:19
update README

BigDong

aac3680
02:37
docs: update MiniCPM5-2B-GPTQ model link in README files

funmaker

b04e640

Sep 6

16:04
docs: update training data and SGLang details

zzh

d312cb6
13:04
docs: update SGLang version requirement

zzh

85dfd5e
11:35
upload MiniCPM5-2B

BigDong

Verified signature
ab8fd77
11:12
initial commit

BigDong

Verified signature
71b5e66

Commit History

Sep 21 29 days ago

Remove the dead `<tool_sep>` branch from chat_template.jinja (fixes OpenBMB/MiniCPM#379)⁠

Sep 12

Enhance README with sampling parameter recommendations and Llama.cpp usage examples

Enhance README with sampling parameter recommendations and Llama.cpp usage examples

Sep 10

Add a LiteRT-LM row to the Deployment cookbook table

Add a LiteRT-LM row to the Deployment cookbook table (#12)⁠

Sep 9

docs: update README

add `MiniCPM5-2B-DSpark-GGUF`

Sep 8

add the LiteRT-LM version of MiniCPM5-2B

docs: update links of `Just RL II` and formatting in README files for clarity and consistency

Sep 7

update README

update README

update README

docs: update MiniCPM5-2B-GPTQ model link in README files

Sep 6

docs: update training data and SGLang details

docs: update SGLang version requirement

upload MiniCPM5-2B

initial commit