Sentence Similarity
sentence-transformers
Safetensors
English
bert
feature-extraction
Generated from Trainer
dataset_size:6300
loss:MatryoshkaLoss
loss:MultipleNegativesRankingLoss
Eval Results (legacy)
text-embeddings-inference
Instructions to use gavinqiangli/bge-base-financial-matryoshka with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use gavinqiangli/bge-base-financial-matryoshka with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("gavinqiangli/bge-base-financial-matryoshka") sentences = [ "Net carrying amount | 10,953 | Less short-term portion | (1,250) | Total long-term portion | $ | 9,703", "How much did restructuring costs amount to in the financial statement?", "How much long-term debt remains after accounting for the short-term portion as of January 29, 2023?", "What are the company's environmental sustainability strategies?" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 691c0cb8eac90da4c2a8f1d9ad288d0bd909ef894b8202166f68cf41d82f606f
- Size of remote file:
- 438 MB
- SHA256:
- a01aa14c116101ba7bb1de15341e70e1f9f96d5b4cec3d35c01392785d4d7f45
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.