Instructions to use enconvo/embeddinggemma-2-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use enconvo/embeddinggemma-2-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download enconvo/embeddinggemma-2-mlx --local-dir embeddinggemma-2-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download README.md from enconvo/embeddinggemma-2-mlx: direct link, hf CLI and curl.
- Browser
- Download file 1.44 kB
-
https://huggingface.co/enconvo/embeddinggemma-2-mlx/resolve/main/README.md
- Command line
-
hf download hf://enconvo/embeddinggemma-2-mlx/README.md
-
curl -L -o README.md https://huggingface.co/enconvo/embeddinggemma-2-mlx/resolve/main/README.md
base_model: google/embeddinggemma-2
library_name: mlx
license: apache-2.0
pipeline_tag: feature-extraction
tags:
- mlx
- embedding
- feature-extraction
- sentence-similarity
- image-feature-extraction
enconvo/embeddinggemma-2-mlx
EmbeddingGemma 2 by Google for MLX, as Enconvo's Local Embeddings runs it on the Mac: text and image encoders, 768-dimensional normalized vectors.
Built from mlx-community/embeddinggemma-2-bf16
(revision 1a4ffddb, converted from Google's revision
914f7f89):
- The audio encoder is removed (
audio_config: null). - The token embedding table (
language_model.embed_tokens) is stored in 8 bits (affine, group size 64): it is only looked up, so this costs no speed. - Every other weight is bf16, unchanged. Keep activations in bf16.
config.json records the quantization of that one module, in mlx-lm's layout.
Checked against the source on a fixed probe set (16 texts, 8 images at soft-token budgets 70, 280): minimum cosine 0.999761 for text and 0.999757 for images.
Use the task prefixes in config_sentence_transformers.json
(task: search result | query: for queries, title: none | text: for
documents). An image is embedded as <bos> <boi> image tokens <eoi> <eos>.
Licence: Apache 2.0, see LICENSE and NOTICE.