Instructions to use openbmb/MiniCPM3-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openbmb/MiniCPM3-4B with Transformers:

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

pipe = pipeline("text-generation", model="openbmb/MiniCPM3-4B", 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/MiniCPM3-4B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use openbmb/MiniCPM3-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openbmb/MiniCPM3-4B"
# 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/MiniCPM3-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openbmb/MiniCPM3-4B

SGLang

How to use openbmb/MiniCPM3-4B 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/MiniCPM3-4B" \
    --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/MiniCPM3-4B",
		"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/MiniCPM3-4B" \
        --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/MiniCPM3-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openbmb/MiniCPM3-4B with Docker Model Runner:
```
docker model run hf.co/openbmb/MiniCPM3-4B
```

vLLM Error: Model architectures ['MiniCPM3ForCausalLM'] are not supported for now.

by HaoyuHuang - opened Sep 6, 2024

Discussion

HaoyuHuang

Sep 6, 2024

vllm version: 0.6.0
vllm-flash-attn: 2.6.1
transformers: 4.44.2
torch: 2.4.0

llm = LLM(
model='./MiniCPM3-4B/',
trust_remote_code=True,
tensor_parallel_size=1
)

ValueError: Model architectures ['MiniCPM3ForCausalLM'] are not supported for now. Supported architectures: ['AquilaModel', 'AquilaForCausalLM', 'BaiChuanForCausalLM', 'BaichuanForCausalLM', 'BloomForCausalLM', 'ChatGLMModel', 'ChatGLMForConditionalGeneration', 'CohereForCausalLM', 'DbrxForCausalLM', 'DeciLMForCausalLM', 'DeepseekForCausalLM', 'DeepseekV2ForCausalLM', 'ExaoneForCausalLM', 'FalconForCausalLM', 'GemmaForCausalLM', 'Gemma2ForCausalLM', 'GPT2LMHeadModel', 'GPTBigCodeForCausalLM', 'GPTJForCausalLM', 'GPTNeoXForCausalLM', 'InternLMForCausalLM', 'InternLM2ForCausalLM', 'JAISLMHeadModel', 'LlamaForCausalLM', 'LLaMAForCausalLM', 'MistralForCausalLM', 'MixtralForCausalLM', 'QuantMixtralForCausalLM', 'MptForCausalLM', 'MPTForCausalLM', 'MiniCPMForCausalLM', 'NemotronForCausalLM', 'OlmoForCausalLM', 'OPTForCausalLM', 'OrionForCausalLM', 'PersimmonForCausalLM', 'PhiForCausalLM', 'Phi3ForCausalLM', 'PhiMoEForCausalLM', 'QWenLMHeadModel', 'Qwen2ForCausalLM', 'Qwen2MoeForCausalLM', 'RWForCausalLM', 'StableLMEpochForCausalLM', 'StableLmForCausalLM', 'Starcoder2ForCausalLM', 'ArcticForCausalLM', 'XverseForCausalLM', 'Phi3SmallForCausalLM', 'MedusaModel', 'EAGLEModel', 'MLPSpeculatorPreTrainedModel', 'JambaForCausalLM', 'GraniteForCausalLM', 'MistralModel', 'Blip2ForConditionalGeneration', 'ChameleonForConditionalGeneration', 'FuyuForCausalLM', 'InternVLChatModel', 'LlavaForConditionalGeneration', 'LlavaNextForConditionalGeneration', 'MiniCPMV', 'PaliGemmaForConditionalGeneration', 'Phi3VForCausalLM', 'UltravoxModel', 'BartModel', 'BartForConditionalGeneration']

neoz

OpenBMB org Sep 6, 2024

For now, you need to install our forked version of vLLM. We have updated the README.

HaoyuHuang

Sep 6, 2024

Thanks! But what do you mean "our forked version of vLLM"? I'm sorry that I couldn't find your content about vLLM in README.md file.

neoz

OpenBMB org Sep 7, 2024

see here:

pip install git+https://github.com/OpenBMB/vllm.git@minicpm3

neoz changed discussion status to closed Sep 18, 2024

JinChe

Sep 20, 2024

see here:

pip install git+https://github.com/OpenBMB/vllm.git@minicpm3

got the error below

subprocess.CalledProcessError: Command '['cmake', '/tmp/pip-req-build-4230nddm', '-G', 'Ninja', '-DCMAKE_BUILD_TYPE=RelWithDebInfo', '-DCMAKE_LIBRARY_OUTPUT_DIRECTORY=/tmp/pip-req-build-4230nddm/build/lib.linux-x86_64-cpython-311/vllm', '-DCMAKE_ARCHIVE_OUTPUT_DIRECTORY=build/temp.linux-x86_64-cpython-311', '-DVLLM_TARGET_DEVICE=cuda', '-DVLLM_PYTHON_EXECUTABLE=/data/aaa/envs/aa_minicpm_py311/bin/python', '-DNVCC_THREADS=1', '-DCMAKE_JOB_POOL_COMPILE:STRING=compile', '-DCMAKE_JOB_POOLS:STRING=compile=128']' returned non-zero exit status 1.
[end of output]

neoz

OpenBMB org Oct 16, 2024

@JinChe vLLM has officially supported MiniCPM3-4B since 0.6.2. You can directly install it using pip.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment