Sentence Similarity
sentence-transformers
Safetensors
bert
feature-extraction
dense
Generated from Trainer
dataset_size:1620956
loss:AnglELoss
Eval Results (legacy)
text-embeddings-inference
Instructions to use biblissima/all-MiniLM-L6-v2_cotes with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use biblissima/all-MiniLM-L6-v2_cotes with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("biblissima/all-MiniLM-L6-v2_cotes") sentences = [ "Paris. Bibliothèque nationale de France, Département des manuscrits, Latin 3085", "Oxford, Bodleian Library, Canon. gr., 051", "Paris. Bibliothèque nationale de France, Collection des manuscrits médiévaux, Latin 3084", "Cracovie, BJ, Ms 1724" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Ctrl+K