Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

facebook
/
MobileMoE-S-Base

Text Generation
Transformers
Safetensors
PyTorch
English
mobilemoe
facebook
meta
mixture-of-experts
MoE
on-device
custom_code
Model card Files Files and versions
xet
Community

Instructions to use facebook/MobileMoE-S-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use facebook/MobileMoE-S-Base with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("text-generation", model="facebook/MobileMoE-S-Base", trust_remote_code=True)
    # Load model directly
    from transformers import AutoModelForCausalLM
    model = AutoModelForCausalLM.from_pretrained("facebook/MobileMoE-S-Base", trust_remote_code=True, device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps Settings
  • vLLM

    How to use facebook/MobileMoE-S-Base with vLLM:

    Install from pip and serve model
    # Install vLLM from pip:
    pip install vllm
    # Start the vLLM server:
    vllm serve "facebook/MobileMoE-S-Base"
    # Call the server using curl (OpenAI-compatible API):
    curl -X POST "http://localhost:8000/v1/completions" \
    	-H "Content-Type: application/json" \
    	--data '{
    		"model": "facebook/MobileMoE-S-Base",
    		"prompt": "Once upon a time,",
    		"max_tokens": 512,
    		"temperature": 0.5
    	}'
    Use Docker
    docker model run hf.co/facebook/MobileMoE-S-Base
  • SGLang

    How to use facebook/MobileMoE-S-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 "facebook/MobileMoE-S-Base" \
        --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": "facebook/MobileMoE-S-Base",
    		"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 "facebook/MobileMoE-S-Base" \
            --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": "facebook/MobileMoE-S-Base",
    		"prompt": "Once upon a time,",
    		"max_tokens": 512,
    		"temperature": 0.5
    	}'
  • Docker Model Runner

    How to use facebook/MobileMoE-S-Base with Docker Model Runner:

    docker model run hf.co/facebook/MobileMoE-S-Base

You need to agree to share your contact information to access this model

The information you provide will be collected, stored, processed and shared in accordance with the Meta Privacy Policy.

Log in or Sign Up to review the conditions and access this model content.

Gated model
You can list files but not access them

Preview of files found in this repository
  • .gitattributes
    1.58 kB
    Add Pareto frontier figure 4 days ago
  • LICENSE
    11.5 kB
    Add FAIR Noncommercial Research License 4 days ago
  • README.md
    9.3 kB
    Add four-stage training recipe figure to model card about 17 hours ago
  • config.json
    1.79 kB
    Add config, generation config and tokenizer 3 days ago
  • configuration_mobilemoe.py
    3.88 kB
    Add MobileMoE modeling code 3 days ago
  • generation_config.json
    180 Bytes
    Add config, generation config and tokenizer 3 days ago
  • mobilemoe_pareto.png
    190 kB
    xet
    Add Pareto frontier figure 4 days ago
  • mobilemoe_recipe.png
    55.3 kB
    Add four-stage training recipe figure to model card about 17 hours ago
  • model.safetensors
    2.53 GB
    xet
    Add files using upload-large-folder tool 3 days ago
  • modeling_mobilemoe.py
    26.2 kB
    Add MobileMoE modeling code 3 days ago
  • special_tokens_map.json
    72 Bytes
    Add config, generation config and tokenizer 3 days ago
  • tokenizer.json
    4.25 MB
    Add config, generation config and tokenizer 3 days ago
  • tokenizer_config.json
    308 Bytes
    Add config, generation config and tokenizer 3 days ago