Image-Text-to-Text
Safetensors
MLX
mlx-vlm
indic_ocr
ocr
document-parsing
layout-analysis
reading-order
indic
Instructions to use HashNuke/indic-ocr-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use HashNuke/indic-ocr-mlx 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("HashNuke/indic-ocr-mlx") config = load_config("HashNuke/indic-ocr-mlx") # 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 weights/ocr/generation_config.json from HashNuke/indic-ocr-mlx: direct link, hf CLI and curl.
- Browser
- Download file 115 Bytes
-
https://huggingface.co/HashNuke/indic-ocr-mlx/resolve/main/weights/ocr/generation_config.json
- Command line
-
hf download hf://HashNuke/indic-ocr-mlx/weights/ocr/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/HashNuke/indic-ocr-mlx/resolve/main/weights/ocr/generation_config.json
115 Bytes
| { | |
| "_from_model_config": true, | |
| "eos_token_id": 262146, | |
| "transformers_version": "5.6.2", | |
| "use_cache": true | |
| } | |