Feature Extraction
MLX
Safetensors
multilingual
embedding_gemma2
mlx-vlm
embedding
sentence-similarity
multimodal
image-feature-extraction
audio-feature-extraction
video-feature-extraction
5-bit
Instructions to use nativ-community/embeddinggemma-2-5bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use nativ-community/embeddinggemma-2-5bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download nativ-community/embeddinggemma-2-5bit --local-dir embeddinggemma-2-5bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download model.safetensors from nativ-community/embeddinggemma-2-5bit: direct link, hf CLI and curl.
- Browser
- Download file 1.13 GB
-
https://huggingface.co/nativ-community/embeddinggemma-2-5bit/resolve/main/model.safetensors
- Command line
-
hf download hf://nativ-community/embeddinggemma-2-5bit/model.safetensors
-
curl -L -o model.safetensors https://huggingface.co/nativ-community/embeddinggemma-2-5bit/resolve/main/model.safetensors
1.13 GB
- Xet hash:
- 5ddaebf6a0c98932c27230a5bc3c4b6c0d96e9a52305216f648b61a08416fe24
- Size of remote file:
- 1.13 GB
- SHA256:
- b044510bd7e383369681e2e8dd87846c847c56f273bd60bdd3d0789da0b8624a
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.