Image-Text-to-Text
MLX
Core ML
apple
ocr
document-parsing
multi-page
deepseek-ocr
Mixture of Experts
fluidinference
Instructions to use FluidInference/unlimited-ocr-mlx-coreml with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use FluidInference/unlimited-ocr-mlx-coreml 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("FluidInference/unlimited-ocr-mlx-coreml") config = load_config("FluidInference/unlimited-ocr-mlx-coreml") # 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
- Atomic Chat
Download config.json from FluidInference/unlimited-ocr-mlx-coreml: direct link, hf CLI and curl.
- Browser
- Download file 704 Bytes
-
https://huggingface.co/FluidInference/unlimited-ocr-mlx-coreml/resolve/main/config.json
- Command line
-
hf download hf://FluidInference/unlimited-ocr-mlx-coreml/config.json
-
curl -L -o config.json https://huggingface.co/FluidInference/unlimited-ocr-mlx-coreml/resolve/main/config.json
704 Bytes
| { | |
| "base_model": "baidu/Unlimited-OCR", | |
| "format": "coreml", | |
| "weights": "decoder int8 per-block-32, page encoder fp16", | |
| "hidden_size": 1280, | |
| "head_dim": 128, | |
| "layers": 12, | |
| "vocab_size": 129280, | |
| "vocab_half": 64640, | |
| "rope_theta": 10000.0, | |
| "ring": 128, | |
| "chunk": 128, | |
| "capacities": [ | |
| 384, | |
| 640, | |
| 1152, | |
| 2304 | |
| ], | |
| "page_tokens": 273, | |
| "image_size": 1024, | |
| "bos_id": 0, | |
| "eos_id": 1, | |
| "image_token_id": 128815, | |
| "prompt_suffix_ids": { | |
| "multi": [ | |
| 37460, | |
| 4366, | |
| 76466, | |
| 16 | |
| ], | |
| "single": [ | |
| 34030, | |
| 76466, | |
| 16 | |
| ] | |
| }, | |
| "ngram_size": 35, | |
| "ngram_window": 1024, | |
| "max_length": 32768, | |
| "decoder": "UnlimitedOcrDecoder.mlpackage", | |
| "encoder": "UnlimitedOcrPageEncoder.mlpackage" | |
| } |