Instructions to use mlx-community/docling-layout-heron-101-mlx-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/docling-layout-heron-101-mlx-bf16 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download mlx-community/docling-layout-heron-101-mlx-bf16 --local-dir docling-layout-heron-101-mlx-bf16
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Initial MLX bf16 conversion of docling-layout-heron-101 (ResNet-101-vd backbone) via mlx_vlm.models.rt_detr_v2
cb895c3 verified Download preprocessor_config.json from mlx-community/docling-layout-heron-101-mlx-bf16: direct link, hf CLI and curl.
- Browser
- Download file 444 Bytes
-
https://huggingface.co/mlx-community/docling-layout-heron-101-mlx-bf16/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://mlx-community/docling-layout-heron-101-mlx-bf16/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/mlx-community/docling-layout-heron-101-mlx-bf16/resolve/main/preprocessor_config.json
444 Bytes
| { | |
| "do_convert_annotations": true, | |
| "do_normalize": false, | |
| "do_pad": false, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "format": "coco_detection", | |
| "image_mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "image_processor_type": "RTDetrImageProcessor", | |
| "image_std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| "pad_size": null, | |
| "resample": 2, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "height": 640, | |
| "width": 640 | |
| } | |
| } | |