Image-Text-to-Text
MLX
Safetensors
multilingual
internvl_chat
vision-language
ocr
document-intelligence
qianfan
apple-silicon
custom_code
Eval Results
4-bit precision
Instructions to use jason1966/Qianfan-OCR-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use jason1966/Qianfan-OCR-MLX-4bit 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("jason1966/Qianfan-OCR-MLX-4bit") config = load_config("jason1966/Qianfan-OCR-MLX-4bit") # 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
| - dataset: | |
| id: allenai/olmOCR-bench | |
| task_id: overall | |
| value: 79.8 | |
| source: | |
| url: https://huggingface.co/papers/2603.13398 | |
| name: Qianfan-OCR technical report | |
| user: nielsr | |
| - dataset: | |
| id: allenai/olmOCR-bench | |
| task_id: arxiv_math | |
| value: 80.1 | |
| source: | |
| url: https://huggingface.co/papers/2603.13398 | |
| name: Qianfan-OCR technical report | |
| user: nielsr | |
| - dataset: | |
| id: allenai/olmOCR-bench | |
| task_id: old_scans_math | |
| value: 73.1 | |
| source: | |
| url: https://huggingface.co/papers/2603.13398 | |
| name: Qianfan-OCR technical report | |
| user: nielsr | |
| - dataset: | |
| id: allenai/olmOCR-bench | |
| task_id: table_tests | |
| value: 81.6 | |
| source: | |
| url: https://huggingface.co/papers/2603.13398 | |
| name: Qianfan-OCR technical report | |
| user: nielsr | |
| - dataset: | |
| id: allenai/olmOCR-bench | |
| task_id: old_scans | |
| value: 42.0 | |
| source: | |
| url: https://huggingface.co/papers/2603.13398 | |
| name: Qianfan-OCR technical report | |
| user: nielsr | |
| - dataset: | |
| id: allenai/olmOCR-bench | |
| task_id: multi_column | |
| value: 80.4 | |
| source: | |
| url: https://huggingface.co/papers/2603.13398 | |
| name: Qianfan-OCR technical report | |
| user: nielsr | |
| - dataset: | |
| id: allenai/olmOCR-bench | |
| task_id: long_tiny_text | |
| value: 89.1 | |
| source: | |
| url: https://huggingface.co/papers/2603.13398 | |
| name: Qianfan-OCR technical report | |
| user: nielsr | |
| - dataset: | |
| id: allenai/olmOCR-bench | |
| task_id: headers_footers | |
| value: 92.2 | |
| source: | |
| url: https://huggingface.co/papers/2603.13398 | |
| name: Qianfan-OCR technical report | |
| user: nielsr | |
| - dataset: | |
| id: allenai/olmOCR-bench | |
| task_id: baseline | |
| value: 99.6 | |
| source: | |
| url: https://huggingface.co/papers/2603.13398 | |
| name: Qianfan-OCR technical report | |
| user: nielsr |