Harder Tasks Need More Experts: Dynamic Routing in MoE Models
Paper • 2403.07652 • Published
Model weights For the Paper ""Harder Tasks Need More Experts: Dynamic Routing in MoE Models""
Inference Code can be found at: https://github.com/ZhenweiAn/Dynamic_MoE
@article{huang2024harder,
title={Harder Tasks Need More Experts: Dynamic Routing in MoE Models},
author={Huang, Quzhe and An, Zhenwei and Zhuang, Nan and Tao, Mingxu and Zhang, Chen and Jin, Yang and Xu, Kun and Chen, Liwei and Huang, Songfang and Feng, Yansong},
journal={arXiv preprint arXiv:2403.07652},
year={2024}
}
- Downloads last month
- 11
Install from pip and serve model
# Install vLLM from pip: pip install vllm# Start the vLLM server: vllm serve "AnLan577/Dynamic_MoE"# Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AnLan577/Dynamic_MoE", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'