Sentence Similarity
sentence-transformers
Safetensors
mpnet
feature-extraction
Generated from Trainer
dataset_size:800
loss:TripletLoss
text-embeddings-inference
Instructions to use edubm/vis-sim-triplets-mpnet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use edubm/vis-sim-triplets-mpnet with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("edubm/vis-sim-triplets-mpnet") sentences = [ "What is the advice given about the use of color in dataviz?", "Don't use color if they communicate nothing.", "Four problems with Pie Charts are detailed in a guide by iCharts.net.", "Always use bright colors for highlighting important data." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 8e294363daddadb447061e2c6d8b47d752dbf9a41afb41947d44e17d72e54353
- Size of remote file:
- 438 MB
- SHA256:
- 0e75b1b19a25cd119a489a2533939877edee040900b401701ddda3d863261419
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.