Sentence Similarity
sentence-transformers
Safetensors
gemma3_text
mirror
embeddinggemma
busco
text-embeddings-inference
Instructions to use busco-app/embeddinggemma-300m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use busco-app/embeddinggemma-300m with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("busco-app/embeddinggemma-300m") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Mirror google/embeddinggemma-300m at 57c266a740f537b4dc058e1b0cda161fd15afa75 (weights unmodified)
80d1ba7 verified Download 1_Pooling/config.json from busco-app/embeddinggemma-300m: direct link, hf CLI and curl.
- Browser
- Download file 312 Bytes
-
https://huggingface.co/busco-app/embeddinggemma-300m/resolve/main/1_Pooling/config.json
- Command line
-
hf download hf://busco-app/embeddinggemma-300m/1_Pooling/config.json
-
curl -L -o config.json https://huggingface.co/busco-app/embeddinggemma-300m/resolve/main/1_Pooling/config.json
312 Bytes
| { | |
| "word_embedding_dimension": 768, | |
| "pooling_mode_cls_token": false, | |
| "pooling_mode_mean_tokens": true, | |
| "pooling_mode_max_tokens": false, | |
| "pooling_mode_mean_sqrt_len_tokens": false, | |
| "pooling_mode_weightedmean_tokens": false, | |
| "pooling_mode_lasttoken": false, | |
| "include_prompt": true | |
| } |