Image-Text-to-Text
MLX
Safetensors
multilingual
unlimited-ocr
baidu
vision-language
ocr
custom_code
mlx-vlm
quantized
affine-quantization
8-bit precision
conversational
8-bit precision
Instructions to use mlx-community/Unlimited-OCR-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/Unlimited-OCR-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("mlx-community/Unlimited-OCR-8bit") config = load_config("mlx-community/Unlimited-OCR-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) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
docs: update links after mlx-community transfer
Browse files
README.md
CHANGED
|
@@ -61,7 +61,7 @@ aimd scan.pdf --task ocr --model unlimited_ocr_8bit
|
|
| 61 |
```bash
|
| 62 |
pip install -U "mlx-vlm>=0.6.8"
|
| 63 |
python -m mlx_vlm.generate \
|
| 64 |
-
--model
|
| 65 |
--image scan.png \
|
| 66 |
--prompt "document parsing." \
|
| 67 |
--max-tokens 8192 \
|
|
@@ -74,10 +74,10 @@ Unlimited-OCR support first shipped in `mlx-vlm 0.6.4`; `0.6.8` or newer is reco
|
|
| 74 |
|
| 75 |
| Precision | Repository | Size |
|
| 76 |
|---|---|---:|
|
| 77 |
-
| 4bit | [`
|
| 78 |
-
| 6bit | [`
|
| 79 |
-
| 8bit | [`
|
| 80 |
-
| bf16 | [`
|
| 81 |
|
| 82 |
## License and attribution
|
| 83 |
|
|
|
|
| 61 |
```bash
|
| 62 |
pip install -U "mlx-vlm>=0.6.8"
|
| 63 |
python -m mlx_vlm.generate \
|
| 64 |
+
--model mlx-community/Unlimited-OCR-8bit \
|
| 65 |
--image scan.png \
|
| 66 |
--prompt "document parsing." \
|
| 67 |
--max-tokens 8192 \
|
|
|
|
| 74 |
|
| 75 |
| Precision | Repository | Size |
|
| 76 |
|---|---|---:|
|
| 77 |
+
| 4bit | [`mlx-community/Unlimited-OCR-4bit`](https://huggingface.co/mlx-community/Unlimited-OCR-4bit) | 2.29 GiB |
|
| 78 |
+
| 6bit | [`mlx-community/Unlimited-OCR-6bit`](https://huggingface.co/mlx-community/Unlimited-OCR-6bit) | 2.98 GiB |
|
| 79 |
+
| 8bit | [`mlx-community/Unlimited-OCR-8bit`](https://huggingface.co/mlx-community/Unlimited-OCR-8bit) | 3.66 GiB |
|
| 80 |
+
| bf16 | [`mlx-community/Unlimited-OCR-bf16`](https://huggingface.co/mlx-community/Unlimited-OCR-bf16) | 6.22 GiB |
|
| 81 |
|
| 82 |
## License and attribution
|
| 83 |
|