Created
February 1, 2024 20:56
-
-
Save pszemraj/7c0a9aa9cabeab9e9f8a03ae2a797f4b to your computer and use it in GitHub Desktop.
download and run this periodically during setup so Colab doesn't whine about you not using the GPU
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# pip install sentence-transformers -q | |
# source: https://www.sbert.net/docs/usage/semantic_textual_similarity.html | |
from sentence_transformers import SentenceTransformer, util | |
model = SentenceTransformer("all-MiniLM-L6-v2") | |
# Two lists of sentences | |
sentences1 = [ | |
"The cat sits outside", | |
"A man is playing guitar", | |
"The new movie is awesome", | |
] | |
sentences2 = [ | |
"The dog plays in the garden", | |
"A woman watches TV", | |
"The new movie is so great", | |
] | |
# Compute embedding for both lists | |
embeddings1 = model.encode(sentences1, convert_to_tensor=True) | |
embeddings2 = model.encode(sentences2, convert_to_tensor=True) | |
# Compute cosine-similarities | |
cosine_scores = util.cos_sim(embeddings1, embeddings2) | |
# Output the pairs with their score | |
for i in range(len(sentences1)): | |
print("{} \t\t {} \t\t Score: {:.4f}".format( | |
sentences1[i], sentences2[i], cosine_scores[i][i] | |
)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment