Image-Text-to-Text
MLX
Safetensors
multilingual
GOT
ocr
ocr2.0
vision-language
got
custom_code
8-bit precision
Instructions to use mlx-community/GOT-OCR2_0-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/GOT-OCR2_0-8bit 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/GOT-OCR2_0-8bit") config = load_config("mlx-community/GOT-OCR2_0-8bit") # 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
| { | |
| "added_tokens_decoder": {}, | |
| "auto_map": { | |
| "AutoTokenizer": [ | |
| "tokenization_qwen.QWenTokenizer", | |
| null | |
| ] | |
| }, | |
| "backend": "custom", | |
| "clean_up_tokenization_spaces": true, | |
| "is_local": true, | |
| "local_files_only": false, | |
| "model_max_length": 8000, | |
| "pad_token": "<|endoftext|>", | |
| "padding_side": "right", | |
| "tokenizer_class": "QWenTokenizer" | |
| } | |