Sentence Similarity
sentence-transformers
Safetensors
bert
feature-extraction
dense
Generated from Trainer
dataset_size:21470
loss:MultipleNegativesRankingLoss
Eval Results (legacy)
text-embeddings-inference
Instructions to use redis/unified-negatives with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use redis/unified-negatives with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("redis/unified-negatives") sentences = [ "This positive resistance model is a different way of analyzing feedback oscillator operation.", "This positive resistance model is a different way of analyzing feedback oscillator operation.", "This negative resistance model is an alternate way of analyzing feedback oscillator operation.", "I am BE 8th sem. CSE student. Which path should I choose as a career or which course I should do to get a good job in future within my country?" ] 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 | |
| } |