gte-multilingual-base-turkish

Turkish SentenceTransformer

A Sentence Transformer fine-tuned on a Turkish dataset.

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("alpecevit/gte-multilingual-base-turkish")
# Run inference
sentences = [
    'Yeşil gömlekli iki kadın, biri kırmızı gözlüklü, dışarıda bir etkinlik izliyor ve gülümsüyor.',
    'yeşil iki kadın',
    'Bayanlar modaya uygun görünmeye çalışıyor.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.7690, 0.6539],
#         [0.7690, 1.0000, 0.5728],
#         [0.6539, 0.5728, 1.0000]])

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}