tooka-sbert-large-v2-legal-names-bi-encoder

pip install -U sentence-transformers

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("IRI2070/tooka-sbert-large-v2-legal-names-bi-encoder")

sentences = [
    'دبیرستان معلم پارسیان',
    'دبیرستان معلم پارسیان‌ها',
    'دبیرستان فرهنگ و معلم',
]

embeddings = model.encode(sentences)
print(embeddings)

# محاسبه شباهت میان جملات
from sentence_transformers.util import cos_sim
similarities = cos_sim(embeddings, embeddings)
print(similarities)