Instructions to use LINs-lab/DynMoE-Phi-2-2.7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LINs-lab/DynMoE-Phi-2-2.7B with Transformers:

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

pipe = pipeline("text-generation", model="LINs-lab/DynMoE-Phi-2-2.7B", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("LINs-lab/DynMoE-Phi-2-2.7B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LINs-lab/DynMoE-Phi-2-2.7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LINs-lab/DynMoE-Phi-2-2.7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LINs-lab/DynMoE-Phi-2-2.7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/LINs-lab/DynMoE-Phi-2-2.7B

SGLang

How to use LINs-lab/DynMoE-Phi-2-2.7B 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 "LINs-lab/DynMoE-Phi-2-2.7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LINs-lab/DynMoE-Phi-2-2.7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "LINs-lab/DynMoE-Phi-2-2.7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LINs-lab/DynMoE-Phi-2-2.7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use LINs-lab/DynMoE-Phi-2-2.7B with Docker Model Runner:
```
docker model run hf.co/LINs-lab/DynMoE-Phi-2-2.7B
```

Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models

If our project helps you, please give us a star ⭐ on GitHub and cite our paper!

📰 News

[2025.01.23]: 🎉 Our paper is accepted to ICLR 2025!
[2024.05.25] 🔥 Our checkpoints are available now!
[2024.05.23] 🔥 Our paper is released!

😎 What's Interesting?

Dynamic Mixture of Experts (DynMoE) incorporates (1) a novel gating method that enables each token to automatically determine the number of experts to activate. (2) An adaptive process automatically adjusts the number of experts during training.

Top-Any Gating

Adaptive Training Process

💡 Model Details

🤔 DynMoE-Phi-2 is a MoE model with dynamic top-k gating, finetuned on LanguageBind/MoE-LLaVA-Phi2-Stage2.
🚀 Our DynMoE-Phi-2-2.7B has totally 5.3B parameters, but only 3.4B are activated! (average top-k = 1.68)
⌛ With the DynMoE tuning stage, we can complete training on 8 A100 GPUs within 2 days.

👍 Acknowledgement

We are grateful for the following awesome projects:

🔒 License

This project is released under the Apache-2.0 license as found in the LICENSE file.

✏️ Citation

@misc{guo2024dynamic,
      title={Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models}, 
      author={Yongxin Guo and Zhenglin Cheng and Xiaoying Tang and Tao Lin},
      year={2024},
      eprint={2405.14297},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}

Star History

Downloads last month: 12

Safetensors

Model size

6B params

Tensor type

BF16

F32

Collection including LINs-lab/DynMoE-Phi-2-2.7B

DynMoE Family

Collection

DynMoE model checkpoints and paper on huggingface • 4 items • Updated Aug 19, 2024 • 4

Paper for LINs-lab/DynMoE-Phi-2-2.7B

Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models

Paper • 2405.14297 • Published May 23, 2024 • 3