Sentence Similarity
sentence-transformers
Safetensors
English
bert
feature-extraction
dataset_size:1K<n<10K
loss:MatryoshkaLoss
loss:MultipleNegativesRankingLoss
Eval Results (legacy)
text-embeddings-inference
Instructions to use philschmid/bge-base-financial-matryoshka with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use philschmid/bge-base-financial-matryoshka with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("philschmid/bge-base-financial-matryoshka") sentences = [ "What begins on page 105 of this report?", "What sections are included alongside the Financial Statements in this report?", "How did net revenues change from 2021 to 2022 on a FX-Neutral basis?", "How much did MedTech's sales increase in 2023 compared to 2022?" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Inference
- Notebooks
- Google Colab
- Kaggle