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/tokenizer_config.json from HashNuke/indic-ocr-mlx: direct link, hf CLI and curl.
- Browser
- Download file 1.08 kB
-
https://huggingface.co/HashNuke/indic-ocr-mlx/resolve/main/weights/ocr/tokenizer_config.json
- Command line
-
hf download hf://HashNuke/indic-ocr-mlx/weights/ocr/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/HashNuke/indic-ocr-mlx/resolve/main/weights/ocr/tokenizer_config.json
1.08 kB
| { | |
| "backend": "tokenizers", | |
| "boi_token": "<|start_of_image|>", | |
| "bos_token": "[@BOS@]", | |
| "clean_up_tokenization_spaces": false, | |
| "eoi_token": "<|end_of_image|>", | |
| "eos_token": "<|im_end|>", | |
| "extra_special_tokens": [ | |
| "<|endoftext|>", | |
| "<|im_start|>", | |
| "<|im_end|>", | |
| "<|object_ref_start|>", | |
| "<|object_ref_end|>", | |
| "<|box_start|>", | |
| "<|box_end|>", | |
| "<|quad_start|>", | |
| "<|quad_end|>", | |
| "<|vision_start|>", | |
| "<|vision_end|>", | |
| "<|image_pad|>", | |
| "<|video_pad|>" | |
| ], | |
| "image_token": "<|image_pad|>", | |
| "is_local": true, | |
| "local_files_only": false, | |
| "model_max_length": 1000000000000000019884624838656, | |
| "model_specific_special_tokens": { | |
| "boi_token": "<|start_of_image|>", | |
| "eoi_token": "<|end_of_image|>", | |
| "image_token": "<|image_pad|>" | |
| }, | |
| "pad_token": "<|endoftext|>", | |
| "padding_side": "right", | |
| "processor_class": "Qwen3VLProcessor", | |
| "sp_model_kwargs": null, | |
| "spaces_between_special_tokens": false, | |
| "tokenizer_class": "TokenizersBackend", | |
| "unk_token": "<unk>", | |
| "use_default_system_prompt": false | |
| } | |