Image-Text-to-Text
MLX
Safetensors
unlimited-ocr
ax-engine
mlx-vlm
ocr
mxfp8
int8
apple-silicon
automatosx
conversational
8-bit precision
Instructions to use AutomatosX/AX-Unlimited-OCR-3B-MoE-MLX-MXFP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use AutomatosX/AX-Unlimited-OCR-3B-MoE-MLX-MXFP8 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("AutomatosX/AX-Unlimited-OCR-3B-MoE-MLX-MXFP8") config = load_config("AutomatosX/AX-Unlimited-OCR-3B-MoE-MLX-MXFP8") # 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
| { | |
| "do_sample": false, | |
| "temperature": 0.0, | |
| "top_p": 1.0, | |
| "max_new_tokens": 8192, | |
| "repetition_penalty": 1.0, | |
| "no_repeat_ngram_size": 35, | |
| "use_cache": true, | |
| "_comment": "Tested default generation parameters for Unlimited-OCR MLX. Deterministic decoding recommended for OCR accuracy.", | |
| "_profiles": { | |
| "accurate": {"max_new_tokens": 8192, "temperature": 0.0, "no_repeat_ngram_size": 35}, | |
| "fast": {"max_new_tokens": 2048, "temperature": 0.0, "no_repeat_ngram_size": 35}, | |
| "long-document": {"max_new_tokens": 16384, "temperature": 0.0, "repetition_penalty": 1.05, "no_repeat_ngram_size": 25}, | |
| "plain-text": {"max_new_tokens": 4096, "temperature": 0.0, "no_repeat_ngram_size": 35}, | |
| "markdown": {"max_new_tokens": 8192, "temperature": 0.0, "no_repeat_ngram_size": 35} | |
| } | |
| } | |