Instructions to use openbmb/MiniCPM5-1B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openbmb/MiniCPM5-1B-Base with Transformers:

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

pipe = pipeline("text-generation", model="openbmb/MiniCPM5-1B-Base")
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/MiniCPM5-1B-Base")
model = AutoModelForCausalLM.from_pretrained("openbmb/MiniCPM5-1B-Base", 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/MiniCPM5-1B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openbmb/MiniCPM5-1B-Base"
# 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/MiniCPM5-1B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openbmb/MiniCPM5-1B-Base

SGLang

How to use openbmb/MiniCPM5-1B-Base 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/MiniCPM5-1B-Base" \
    --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/MiniCPM5-1B-Base",
		"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/MiniCPM5-1B-Base" \
        --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/MiniCPM5-1B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openbmb/MiniCPM5-1B-Base with Docker Model Runner:
```
docker model run hf.co/openbmb/MiniCPM5-1B-Base
```

OpenBMB-LLM commited on May 24

Commit

0ff46ea

verified ·

1 Parent(s): f731357

Update Chinese model card (README-cn.md)

Browse files

Files changed (1) hide show

README-cn.md +1 -3

README-cn.md CHANGED Viewed

@@ -75,9 +75,7 @@ MiniCPM5-1B 具有以下特性：
 ## 简介
-MiniCPM5-1B 是一款紧凑的稠密 decoder-only Transformer，训练目标是提升 1B 参数量级下的输出质量。模型沿用标准 `LlamaForCausalLM` 架构（24 层、GQA 8:1、原生 128K 上下文、1,080,632,832 参数），可以在 Transformers、vLLM、SGLang、llama.cpp、MLX、Ollama、LM Studio 等主流推理后端中直接加载，无需自定义算子。
-完整架构细节与按组件参数拆解见 GitHub 上的 [Transformers 部署 cookbook](https://github.com/OpenBMB/MiniCPM/blob/minicpm5/docs/deployment/transformers.md)。
 ## 评测结果

 ## 简介
+MiniCPM5-1B 是 MiniCPM5 系列的首个模型，面向本地助手、coding agent、工具调用流程以及需要紧凑模型的推理场景。它在较小部署成本下提供原生长上下文能力，并通过同一份权重支持 Think / No Think 两种对话模式。
 ## 评测结果