Sentence Similarity
sentence-transformers
Safetensors
bert
feature-extraction
dense
Generated from Trainer
dataset_size:790756
loss:MultipleNegativesSymmetricRankingLoss
Eval Results (legacy)
text-embeddings-inference
Instructions to use LamaDiab/MiniLM-v35-SemanticEngine with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use LamaDiab/MiniLM-v35-SemanticEngine with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("LamaDiab/MiniLM-v35-SemanticEngine") sentences = [ "creamy black varnish for black leathers", "shoe accessory", "the first product scented, nourishing, polishing and preserving all types of leather 50 gr.", "steal the scene t-shirt" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
| { | |
| "word_embedding_dimension": 384, | |
| "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 | |
| } |