← All models

sentence-transformers

Sentence Transformers: all-mpnet-base-v2

The all-mpnet-base-v2 embedding model encodes sentences and short paragraphs into a 768-dimensional dense vector space, providing high-fidelity semantic embeddings well suited for tasks like information retrieval, clustering, similarity scoring, and text ranking.

Try in playgroundAPI reference
8,192 context
Modalities:text->embeddings
Released:11/17/2025

The all-mpnet-base-v2 embedding model encodes sentences and short paragraphs into a 768-dimensional dense vector space, providing high-fidelity semantic embeddings well suited for tasks like information retrieval, clustering, similarity scoring, and text ranking.

Weekly tokens

33.8M

Tokens generated this week (network-wide)

Usage by period

No ranking data yet for this model.