sentence-transformers

/

all-MiniLM-L6-v2

like 2.3k

Hello!

If you have Python installed, then you can run:

pip install sentence-transformers

to install the Sentence Transformers package which allows easy access to these models.

Then, you can use the model like so:

from sentence_transformers import SentenceTransformer

# 1. Load a pretrained Sentence Transformer model
model = SentenceTransformer("all-MiniLM-L6-v2")

# The sentences to encode
sentences = [
    "The weather is lovely today.",
    "It's so sunny outside!",
    "He drove to the stadium.",
]

# 2. Calculate embeddings by calling model.encode()
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# 3. Calculate the embedding similarities
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.6660, 0.1046],
#         [0.6660, 1.0000, 0.1411],
#         [0.1046, 0.1411, 1.0000]])

Hope this helps!

• Tom Aarsen

Hey @tomaarsen ,

Thank you for your input. But I want to run this model offline on my system. The approach you suggested is still using the API.

The approach I described actually downloads the model weights locally and computes the embeddings on your CPU or GPU.

• Tom Aarsen

@tomaarsen Oh, I just realized that. Thank you.
However, I believe the model restarts each time. I would like to run it on my own system to avoid the startup delay.