Jina Embedding v1 Small English
Jina Embedding v1 Small is an English sentence embedding model with 35 million parameters and 512-dimensional output. Jina's Finetuner team trained the family for retrieval and textual similarity.
How the model works
The release uses Linnaeus-Clean, a collection of 380 million sentence pairs selected from a larger 1.6-billion-pair source. It includes query-document pairs across several domains. The weights use Apache 2.0 and can run with Sentence Transformers or Jina's historical Finetuner tooling.Jina Embedding v1 Small English model details
Use and access
Small sits between the 14-million-parameter Tiny and 110-million-parameter Base. Its 512-dimensional vectors form a different representation from either neighboring size; query and document encoding must use the same model.Jina Embedding v1 Small English model details
Specifications & access
| Detail | Value and conditions |
|---|---|
| Launch date | |
| Access | Downloadable |
| Model identifiers | jina-embedding-s-en-v1jinaai/jina-embedding-s-en-v1 |
| Parameters | 35 millionJina Embedding v1 Small English model details |
| Embedding dimensions | 512Jina Embedding v1 Small English model details |
| Weight license | Apache 2.0Jina Embedding v1 Small English model details |
Related models
- Jina Embeddings v2 Small English
Jina AI ยท Jina Embeddings v2
A 33-million-parameter English encoder with long-document input.
Launch date Downloadable