Sentence Similarity
sentence-transformers
Safetensors
English
distilbert
feature-extraction
loss:TripletLoss
Eval Results (legacy)
text-embeddings-inference
Instructions to use tomaarsen/distilbert-base-uncased-wikipedia-sections-triplet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use tomaarsen/distilbert-base-uncased-wikipedia-sections-triplet with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("tomaarsen/distilbert-base-uncased-wikipedia-sections-triplet") sentences = [ "All charts rank the top 100.", "There are two primary charts: Gaon Album Chart and Gaon Digital Chart.", "Regional Preferente de Cataluña (3): 1999-00, 2002-03, 2008-09.", "Kyūsaku was born in Fukuoka city, Fukuoka prefecture as Sugiyama Naoki." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 5a24b77e9f61c75e81a83168ea9e6449c25137be751b8cfc4d7e3af4ae43df16
- Size of remote file:
- 265 MB
- SHA256:
- a985c446b3479442ff89f4e7e82a1393809d2288eec64a61cc2580b84040ce4a
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.