Image-Text-to-Text
MLX
Safetensors
oxr
mlx-vlm
ocr
document-parsing
apple-silicon
conversational
8-bit precision
Instructions to use npario/OXR-1.0-mlx-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use npario/OXR-1.0-mlx-8bit 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("npario/OXR-1.0-mlx-8bit") config = load_config("npario/OXR-1.0-mlx-8bit") # 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 processor_config.json from npario/OXR-1.0-mlx-8bit: direct link, hf CLI and curl.
- Browser
- Download file 382 Bytes
-
https://huggingface.co/npario/OXR-1.0-mlx-8bit/resolve/main/processor_config.json
- Command line
-
hf download hf://npario/OXR-1.0-mlx-8bit/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/npario/OXR-1.0-mlx-8bit/resolve/main/processor_config.json
382 Bytes
| { | |
| "image_processor": { | |
| "hidden_stride": 2, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_processor_type": "OXRImageProcessor", | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "max_pixels": 921600, | |
| "merge_size": 2, | |
| "min_pixels": 200704, | |
| "patch_size": 16, | |
| "temporal_patch_size": 1 | |
| }, | |
| "processor_class": "OXRProcessor" | |
| } | |