Feature Extraction
MLX
Safetensors
multilingual
embedding_gemma2
embedding
sentence-similarity
code
mlx-vlm
Instructions to use jayyun98/embeddinggemma-2-text-270m-mlx-fp32 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use jayyun98/embeddinggemma-2-text-270m-mlx-fp32 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download jayyun98/embeddinggemma-2-text-270m-mlx-fp32 --local-dir embeddinggemma-2-text-270m-mlx-fp32
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download verification.json from jayyun98/embeddinggemma-2-text-270m-mlx-fp32: direct link, hf CLI and curl.
- Browser
- Download file 1.44 kB
-
https://huggingface.co/jayyun98/embeddinggemma-2-text-270m-mlx-fp32/resolve/main/verification.json
- Command line
-
hf download hf://jayyun98/embeddinggemma-2-text-270m-mlx-fp32/verification.json
-
curl -L -o verification.json https://huggingface.co/jayyun98/embeddinggemma-2-text-270m-mlx-fp32/resolve/main/verification.json
1.44 kB
| { | |
| "status": "passed", | |
| "runtime": "mlx", | |
| "precision": "fp32", | |
| "native_precision_loading_verified": true, | |
| "excluded_encoders_absent": true, | |
| "checks": { | |
| "search_english_korean": { | |
| "shape": [ | |
| 2, | |
| 768 | |
| ], | |
| "min_cosine_vs_source_fp32": 0.9999999999995535, | |
| "max_absolute_difference_vs_source_fp32": 1.2293457984924316e-07 | |
| }, | |
| "documents": { | |
| "shape": [ | |
| 2, | |
| 768 | |
| ], | |
| "min_cosine_vs_source_fp32": 0.9999999999993181, | |
| "max_absolute_difference_vs_source_fp32": 1.4901161193847656e-07 | |
| }, | |
| "code": { | |
| "shape": [ | |
| 2, | |
| 768 | |
| ], | |
| "min_cosine_vs_source_fp32": 0.9999999999992627, | |
| "max_absolute_difference_vs_source_fp32": 1.5366822481155396e-07 | |
| }, | |
| "mrl_128": { | |
| "shape": [ | |
| 2, | |
| 128 | |
| ], | |
| "unit_norm": true | |
| }, | |
| "mrl_256": { | |
| "shape": [ | |
| 2, | |
| 256 | |
| ], | |
| "unit_norm": true | |
| }, | |
| "mrl_512": { | |
| "shape": [ | |
| 2, | |
| 512 | |
| ], | |
| "unit_norm": true | |
| } | |
| }, | |
| "environment": { | |
| "platform": "macOS-26.4-arm64-arm-64bit", | |
| "transformers": "5.19.0", | |
| "sentence_transformers": "6.1.0", | |
| "torch": "2.14.1", | |
| "torch_bf16_device": "mps", | |
| "torch_fp32_device": "cpu", | |
| "mlx": "0.32.3", | |
| "mlx_device": "Apple M5 Pro", | |
| "mlx_vlm_revision": "3d87e88402f307efbf68e568971aa887ee7d9ed0", | |
| "MLX_ENABLE_TF32": "0" | |
| } | |
| } | |