Feature Extraction
MLX
Safetensors
jina_omni_small_mlx
multimodal
embeddings
semantic-search
image
audio
video
apple-silicon
Instructions to use lokimorty/nanobe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use lokimorty/nanobe with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download lokimorty/nanobe --local-dir nanobe
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download model/preprocessor_config.json from lokimorty/nanobe: direct link, hf CLI and curl.
- Browser
- Download file 431 Bytes
-
https://huggingface.co/lokimorty/nanobe/resolve/main/model/preprocessor_config.json
- Command line
-
hf download hf://lokimorty/nanobe/model/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/lokimorty/nanobe/resolve/main/model/preprocessor_config.json
431 Bytes
| { | |
| "image_processor_type": "Qwen2VLImageProcessorFast", | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [0.5, 0.5, 0.5], | |
| "image_std": [0.5, 0.5, 0.5], | |
| "min_pixels": 262144, | |
| "max_pixels": 1310720, | |
| "merge_size": 2, | |
| "patch_size": 16, | |
| "processor_class": "Qwen3VLProcessor", | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "temporal_patch_size": 2 | |
| } | |