tabularisai/Zip-1

Super small embedding model (only 4MB!)

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("tabularisai/Zip-1")
# Run inference
sentences = [
    'The weather is lovely today.',
    "It's so sunny outside!",
    'He drove to the stadium.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 32]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

print(similarities)
#tensor([[1.0000, 0.7272, 0.2864],
#        [0.7272, 1.0000, 0.2265],
#        [0.2864, 0.2265, 1.0000]])