Sentence Similarity
sentence-transformers
Safetensors
bert
feature-extraction
Generated from Trainer
dataset_size:4200100
loss:OrdinalProxyContrastiveLoss
text-embeddings-inference
Instructions to use swardiantara/bert-tiny-amazon_reviews-k5-fixed-euclidean with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use swardiantara/bert-tiny-amazon_reviews-k5-fixed-euclidean with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("swardiantara/bert-tiny-amazon_reviews-k5-fixed-euclidean") sentences = [ "Unless you have this jam-packed full of items, the unit collapses on itself. I never held it's shape therefore, making it hard to reach my items when I needed them. The silver metal pieces on the handle fell off soon after it arrived. I must have missed the \"return by\" date as I now am stuck with it.", "very light weight. thin metal. nice looking just not a quality piece.it was okay for a kids gift. don't see it lasting very long as it will dent easy.", "Good quality gasket and it was packaged well. Fit great as well.", "Fit fine - do not stay up. I haven’t washed or stretched, literally too out of bag and tried on for a bit of walking around the house and within 30 minutes they bunched down. Not sure the elastic will last either. Other than that, colors/patterns and general fabric is nice." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
| [ | |
| { | |
| "idx": 0, | |
| "name": "0", | |
| "path": "", | |
| "type": "sentence_transformers.base.modules.transformer.Transformer" | |
| }, | |
| { | |
| "idx": 1, | |
| "name": "1", | |
| "path": "1_Pooling", | |
| "type": "sentence_transformers.sentence_transformer.modules.pooling.Pooling" | |
| } | |
| ] |