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

Amshaker
/
Mobile-O-0.5B-iOS

Image-Text-to-Text
MLX
Core ML
Safetensors
mobile-o
multimodal
unified-model
ios
on-device
mobile
edge-ai
Model card Files Files and versions
xet
Community

Instructions to use Amshaker/Mobile-O-0.5B-iOS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • MLX

    How to use Amshaker/Mobile-O-0.5B-iOS with MLX:

    # Make sure mlx-vlm is installed
    # pip install --upgrade mlx-vlm
    
    from mlx_vlm import load, generate
    from mlx_vlm.prompt_utils import apply_chat_template
    from mlx_vlm.utils import load_config
    
    # Load the model
    model, processor = load("Amshaker/Mobile-O-0.5B-iOS")
    config = load_config("Amshaker/Mobile-O-0.5B-iOS")
    
    # Prepare input
    image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
    prompt = "Describe this image."
    
    # Apply chat template
    formatted_prompt = apply_chat_template(
        processor, config, prompt, num_images=1
    )
    
    # Generate output
    output = generate(model, processor, formatted_prompt, image)
    print(output)
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps Settings
  • LM Studio
Mobile-O-0.5B-iOS / llm
372 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
Amshaker's picture
Amshaker
Deploy everything on ANE instead of GPU, leading to significantly faster generation speed
56828ca verified 2 months ago
  • added_tokens.json
    140 Bytes
    Release iOS-compatible model components for Mobile-O-0.5B 5 months ago
  • config.json
    510 Bytes
    Deploy everything on ANE instead of GPU, leading to significantly faster generation speed 2 months ago
  • merges.txt
    1.67 MB
    Release iOS-compatible model components for Mobile-O-0.5B 5 months ago
  • model.safetensors
    356 MB
    xet
    Deploy everything on ANE instead of GPU, leading to significantly faster generation speed 2 months ago
  • model.safetensors.index.json
    54.4 kB
    Release iOS-compatible model components for Mobile-O-0.5B 5 months ago
  • preprocessor_config.json
    467 Bytes
    Deploy everything on ANE instead of GPU, leading to significantly faster generation speed 2 months ago
  • special_tokens_map.json
    371 Bytes
    Release iOS-compatible model components for Mobile-O-0.5B 5 months ago
  • tokenizer.json
    11.4 MB
    xet
    Release iOS-compatible model components for Mobile-O-0.5B 5 months ago
  • tokenizer_config.json
    1.88 kB
    Release iOS-compatible model components for Mobile-O-0.5B 5 months ago
  • vocab.json
    2.78 MB
    Release iOS-compatible model components for Mobile-O-0.5B 5 months ago