RepresentLM-v2

This is a sentence-transformers model: It maps sentences and paragraphs to a 768-dimensional dense vector space and can be used for tasks like clustering or semantic search.

The model is trained on the HEADLINES semantic similarity dataset, using the StoriesLM-v2-1979 model as a base.

Usage

First install the sentence-transformers package:

pip install -U sentence-transformers

The model can then be used to encode language sequences:

from sentence_transformers import SentenceTransformer

sequences = ["This is an example sequence", "Each sequence is embedded"]

model = SentenceTransformer("suproteem/RepresentLM-v2")
embeddings = model.encode(sequences)
print(embeddings)