Instructions to use xinrongzhang2022/MiniCPM-duplex with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xinrongzhang2022/MiniCPM-duplex with Transformers:

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

pipe = pipeline("text-generation", model="xinrongzhang2022/MiniCPM-duplex", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("xinrongzhang2022/MiniCPM-duplex", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use xinrongzhang2022/MiniCPM-duplex with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xinrongzhang2022/MiniCPM-duplex"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xinrongzhang2022/MiniCPM-duplex",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xinrongzhang2022/MiniCPM-duplex

SGLang

How to use xinrongzhang2022/MiniCPM-duplex 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 "xinrongzhang2022/MiniCPM-duplex" \
    --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": "xinrongzhang2022/MiniCPM-duplex",
		"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 "xinrongzhang2022/MiniCPM-duplex" \
        --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": "xinrongzhang2022/MiniCPM-duplex",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use xinrongzhang2022/MiniCPM-duplex with Docker Model Runner:
```
docker model run hf.co/xinrongzhang2022/MiniCPM-duplex
```

@misc{zhang2024turnbasedgameenablingrealtime,
      title={Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models}, 
      author={Xinrong Zhang and Yingfa Chen and Shengding Hu and Xu Han and Zihang Xu and Yuanwei Xu and Weilin Zhao and Maosong Sun and Zhiyuan Liu},
      year={2024},
      eprint={2406.15718},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
      url={https://arxiv.org/abs/2406.15718}, 
}

Downloads last month: 1,310

Paper for xinrongzhang2022/MiniCPM-duplex

Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models

Paper • 2406.15718 • Published Jun 22, 2024 • 14