Image-Text-to-Text
MLX
Safetensors
PaddleOCR
English
Chinese
multilingual
paddleocr_vl
ERNIE4.5
PaddlePaddle
image-to-text
ocr
document-parse
layout
table
formula
chart
seal
spotting
conversational
custom_code
8-bit precision
Instructions to use OpenGryd/PaddleOCR-VL-1.6-MLX-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use OpenGryd/PaddleOCR-VL-1.6-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("OpenGryd/PaddleOCR-VL-1.6-MLX-8bit") config = load_config("OpenGryd/PaddleOCR-VL-1.6-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) - PaddleOCR
How to use OpenGryd/PaddleOCR-VL-1.6-MLX-8bit with PaddleOCR:
# See https://www.paddleocr.ai/latest/version3.x/pipeline_usage/PaddleOCR-VL.html to installation from paddleocr import PaddleOCRVL pipeline = PaddleOCRVL(pipeline_version="OpenGryd/PaddleOCR-VL-1.6-MLX-8bit") output = pipeline.predict("path/to/document_image.png") for res in output: res.print() res.save_to_json(save_path="output") res.save_to_markdown(save_path="output") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
preprocessor_config.json: preprocessor/processor config: raise vision max_pixels 1,003,520 -> 4,064,256 (6x6 stage of the 28px/token grid: 5,184 merged-token budget; A4 lands ~5,100; min_pixels unchanged 112,896). Small-text OCR tuning for the zoom-4.0 render lane; lower stages selectable client-side via render scale / crop pixel budget. Deliberate divergence from upstream PaddlePaddle/PaddleOCR-VL-1.6 and mlx-community 1.5/1.6 defaults (1,003,520). Measured on M-series: full-page wall ~5x vs 1.0MP cap, crop lane unaffected, server RSS ~2.2 GB.
b4c87a6 verified Download preprocessor_config.json from OpenGryd/PaddleOCR-VL-1.6-MLX-8bit: direct link, hf CLI and curl.
- Browser
- Download file 641 Bytes
-
https://huggingface.co/OpenGryd/PaddleOCR-VL-1.6-MLX-8bit/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://OpenGryd/PaddleOCR-VL-1.6-MLX-8bit/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/OpenGryd/PaddleOCR-VL-1.6-MLX-8bit/resolve/main/preprocessor_config.json
641 Bytes
| { | |
| "auto_map": { | |
| "AutoImageProcessor": "image_processing_paddleocr_vl.PaddleOCRVLImageProcessor", | |
| "AutoProcessor": "processing_paddleocr_vl.PaddleOCRVLProcessor" | |
| }, | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_processor_type": "PaddleOCRVLImageProcessor", | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "max_pixels": 4064256, | |
| "merge_size": 2, | |
| "min_pixels": 112896, | |
| "patch_size": 14, | |
| "processor_class": "PaddleOCRVLProcessor", | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "temporal_patch_size": 1 | |
| } | |