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
Upload export_config.json with huggingface_hub
Browse files- export_config.json +11 -0
export_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_name": "embeddinggemma-300m-distilled-768dim",
|
| 3 |
+
"base_model": "google/embeddinggemma-300m",
|
| 4 |
+
"embedding_dim": 768,
|
| 5 |
+
"hidden_size": 768,
|
| 6 |
+
"target_hidden_size": null,
|
| 7 |
+
"width_reduction_factor": null,
|
| 8 |
+
"had_projection": false,
|
| 9 |
+
"original_st_output_dim": 768,
|
| 10 |
+
"projection_incorporated": false
|
| 11 |
+
}
|