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

anerjy
/
Step-3.7-Flash-MLX-adapter

Image-Text-to-Text
MLX
step3p7
mlx-vlm
mlx-lm
vision-language
multimodal
apple-silicon
Model card Files Files and versions
xet
Community

Instructions to use anerjy/Step-3.7-Flash-MLX-adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • MLX

    How to use anerjy/Step-3.7-Flash-MLX-adapter 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("anerjy/Step-3.7-Flash-MLX-adapter")
    config = load_config("anerjy/Step-3.7-Flash-MLX-adapter")
    
    # 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
Step-3.7-Flash-MLX-adapter / scripts
11.5 kB
Ctrl+K
Ctrl+K
  • 2 contributors
History: 4 commits
anerjy
P4: MTP working โ€” 75% accept, 15% net speedup (52.6 vs 45.6 tok/s)
7818108 about 1 month ago
  • extract_vision_weights.py
    4.1 kB
    Initial: Step 3.7 Flash MLX adapter (text + vision) about 2 months ago
  • rewrite_mtp_shard.py
    7.43 kB
    P4: MTP working โ€” 75% accept, 15% net speedup (52.6 vs 45.6 tok/s) about 1 month ago