Feature Extraction
sentence-transformers
Safetensors
gemma3_text
text-embeddings
compression
depth-pruning
embedding-width-reduction
retrieval
semantic-search
text-embeddings-inference
Instructions to use Pieces/embeddinggemma-300m-distilled-depth10pct-10-768dim-best with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Pieces/embeddinggemma-300m-distilled-depth10pct-10-768dim-best with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Pieces/embeddinggemma-300m-distilled-depth10pct-10-768dim-best") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Download export_config.json from Pieces/embeddinggemma-300m-distilled-depth10pct-10-768dim-best: direct link, hf CLI and curl.
- Browser
- Download file 310 Bytes
-
https://huggingface.co/Pieces/embeddinggemma-300m-distilled-depth10pct-10-768dim-best/resolve/main/export_config.json
- Command line
-
hf download hf://Pieces/embeddinggemma-300m-distilled-depth10pct-10-768dim-best/export_config.json
-
curl -L -o export_config.json https://huggingface.co/Pieces/embeddinggemma-300m-distilled-depth10pct-10-768dim-best/resolve/main/export_config.json
310 Bytes
| { | |
| "model_name": "embeddinggemma-300m-distilled-768dim", | |
| "base_model": "google/embeddinggemma-300m", | |
| "embedding_dim": 768, | |
| "hidden_size": 768, | |
| "target_hidden_size": null, | |
| "width_reduction_factor": null, | |
| "had_projection": false, | |
| "original_st_output_dim": 768, | |
| "projection_incorporated": false | |
| } |