Feature Extraction
sentence-transformers
Safetensors
gemma3_text
embeddings
retrieval
knowledge-distillation
matryoshka
text-embeddings-inference
Instructions to use Pieces/embeddinggemma-300m-distilled-width10pct-128dim-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-width10pct-128dim-best with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Pieces/embeddinggemma-300m-distilled-width10pct-128dim-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-width10pct-128dim-best: direct link, hf CLI and curl.
- Browser
- Download file 309 Bytes
-
https://huggingface.co/Pieces/embeddinggemma-300m-distilled-width10pct-128dim-best/resolve/main/export_config.json
- Command line
-
hf download hf://Pieces/embeddinggemma-300m-distilled-width10pct-128dim-best/export_config.json
-
curl -L -o export_config.json https://huggingface.co/Pieces/embeddinggemma-300m-distilled-width10pct-128dim-best/resolve/main/export_config.json
309 Bytes
| { | |
| "model_name": "embeddinggemma-300m-distilled-10pct-128dim", | |
| "base_model": "google/embeddinggemma-300m", | |
| "embedding_dim": 128, | |
| "hidden_size": 72, | |
| "target_hidden_size": 72, | |
| "width_reduction_factor": 0.1, | |
| "had_projection": true, | |
| "original_st_output_dim": 72, | |
| "projection_incorporated": true | |
| } |