sentence-transformers How to use arafamustafa/gte-small-similarity with sentence-transformers:
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("arafamustafa/gte-small-similarity")
sentences = [
"Using this advanced technology, we will be able to gain transparency in our elections, without compromising the privacy of voters, and we have a way to accurately demonstrate the mathematical results of elections. Also, at the request of the voter, there will be a way to allow the voter to vote online in the election and follow his vote in the ballot box to ensure that his vote is stored safely and safely without changing or changing it in any way.",
"Using this advanced technology, we will be able to gain transparency in our elections, without compromising the privacy of voters, and we have a way to accurately demonstrate the mathematical results of elections. Also, at the request of the voter, there will be a way to allow the voter to vote online in the election and follow his vote in the ballot box to ensure that his vote is stored safely and safely without changing or changing it in any way.",
"we decided to make a platform, Pharmacies can be far away from your place. After noticing all these problems we made a survey to found a solution for this problem, Health is considering as the important thing in our lives, we find the solution must be the processions of the technology era, like some is not always available, can solve these problems in the side of, we found most of people suffer from a large number of problem include problems that presented previously, we have noticed that there are many problems in medicine field, the prices change from place to another",
"determine the type of project as it was a construction project or an architectural project or sewage project After specifying the name, Enter the name of the project, The platform helps the user to find the appropriate map that he is looking for, type of project He will show him the map of the building as he wants to see it."
]
embeddings = model.encode(sentences)
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [4, 4] 
