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 2_Dense/config.json from Pieces/embeddinggemma-300m-distilled-width10pct-128dim-best: direct link, hf CLI and curl.
- Browser
- Download file 124 Bytes
-
https://huggingface.co/Pieces/embeddinggemma-300m-distilled-width10pct-128dim-best/resolve/main/2_Dense/config.json
- Command line
-
hf download hf://Pieces/embeddinggemma-300m-distilled-width10pct-128dim-best/2_Dense/config.json
-
curl -L -o config.json https://huggingface.co/Pieces/embeddinggemma-300m-distilled-width10pct-128dim-best/resolve/main/2_Dense/config.json
124 Bytes
| { | |
| "in_features": 72, | |
| "out_features": 288, | |
| "bias": false, | |
| "activation_function": "torch.nn.modules.linear.Identity" | |
| } |