BAAI’s (english) embedding model version 1.5 for passage retrieval and sentence similarity, using the Center For Curriculum Redesign’s Replicate Embedding Cog template.
As of September 2023, this model is state of the art.
- output dimensions : 1024
- parameters: 326M
- MTEB score average: 64.23
Dimension | Sequence Length | Average (56) | Retrieval (15) | Clustering (11) | Pair Classification (3) | Reranking (4) | STS (10) | Summarization (1) | Classification (12) |
1024 | 512 | 64.23 | 54.29 | 46.08 | 87.12 | 60.03 | 83.11 | 31.61 | 75.97 |
Usage
See the examples tab.