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

Prophet25200
/
Unlimited-OCR-mlx-4bit

Image-Text-to-Text
MLX
Safetensors
English
deepseekocr
conversational
custom_code
4-bit precision
Model card Files Files and versions
xet
Community

Instructions to use Prophet25200/Unlimited-OCR-mlx-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • MLX

    How to use Prophet25200/Unlimited-OCR-mlx-4bit 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("Prophet25200/Unlimited-OCR-mlx-4bit")
    config = load_config("Prophet25200/Unlimited-OCR-mlx-4bit")
    
    # 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
Unlimited-OCR-mlx-4bit
2.46 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 3 commits
Prophet25200's picture
Prophet25200
Upload folder using huggingface_hub
1561f3c verified 17 days ago
  • .gitattributes
    1.52 kB
    initial commit 17 days ago
  • README.md
    351 Bytes
    Upload folder using huggingface_hub 17 days ago
  • chat_template.jinja
    191 Bytes
    Upload folder using huggingface_hub 17 days ago
  • config.json
    3.51 kB
    Upload folder using huggingface_hub 17 days ago
  • configuration_deepseek_v2.py
    10.7 kB
    Upload folder using huggingface_hub 17 days ago
  • conversation.py
    9.25 kB
    Upload folder using huggingface_hub 17 days ago
  • deepencoder.py
    38 kB
    Upload folder using huggingface_hub 17 days ago
  • model.safetensors
    2.45 GB
    xet
    Upload folder using huggingface_hub 17 days ago
  • model.safetensors.index.json
    72.6 kB
    Upload folder using huggingface_hub 17 days ago
  • modeling_deepseekv2.py
    90.2 kB
    Upload folder using huggingface_hub 17 days ago
  • modeling_unlimitedocr.py
    53.4 kB
    Upload folder using huggingface_hub 17 days ago
  • processor_config.json
    463 Bytes
    Upload folder using huggingface_hub 17 days ago
  • special_tokens_map.json
    801 Bytes
    Upload folder using huggingface_hub 17 days ago
  • tokenizer.json
    9.98 MB
    Upload folder using huggingface_hub 17 days ago
  • tokenizer_config.json
    545 Bytes
    Upload folder using huggingface_hub 17 days ago