all-mpnet-base-v2

This is a sentence-transformers model: This model maps sentences & paragraphs to a 128 dimensional dense vector space and can be used for tasks like clustering or semantic search.

Model performance (Cosine-Similarity based, on the sts-test dataset):

• Original (768 dimensions): Pearson: 0.8404 Spearman: 0.8342
• 128 dimensions: Pearson: 0.8318 Spearman: 0.8361

created using: dimensionality_reduction