Sentence Similarity
sentence-transformers
Safetensors
bert
feature-extraction
dense
Generated from Trainer
dataset_size:3872
loss:MultipleNegativesRankingLoss
Eval Results (legacy)
text-embeddings-inference
Instructions to use HarishMaths/Hotel-Policy-Embedding with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use HarishMaths/Hotel-Policy-Embedding with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("HarishMaths/Hotel-Policy-Embedding") sentences = [ "(g) If a Member wishes to extend their stay and has enough Nightly Upgrade Award(s) to cover the extension, the Member must book a separate reservation for the additional nights and request to use Nightly Upgrade Awards on Marriott Websites or by calling Member Support; the Nightly Upgrade Award request cannot be processed at the Participating Property.", "Flexible rates cancel up to a deadline the property sets.", "DONT book a non-refundable hotel without reading the cancellation policy because you must understand the exact penalty structurewhether you forfeit one night, the full amount, or a percentageto determine your coverage needs and ensure your insurance limit is adequate.", "As for semi-flexible plans, they might require notice at least five days before check-in." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Ctrl+K