Jina Embeddings v2 Base German-English
Jina Embeddings v2 Base German-English is a JinaBERT encoder with an 8,192-token input window. It creates pooled vectors for semantic search and similarity, rather than generating an answer.
How the model works
Jina designed the bilingual training for German-only, English-only and cross-language retrieval. Mixed German-English text is an explicit target, rather than an incidental use of a general multilingual encoder.Jina Embeddings v2 Base German-English model details
Use and access
The Apache 2.0 download uses mean pooling and the JinaBERT implementation. Its extended input length comes from symmetric bidirectional ALiBi. This entry preserves the specific trained checkpoint. Later models with different dimensions or training should not be substituted into an existing vector index without rebuilding compatible representations.Jina Embeddings v2 Base German-English model detailsJina Embeddings v2 Base German-English technical overview
Specifications & access
| Detail | Value and conditions |
|---|---|
| Launch date | |
| Access | Downloadable |
| Model identifiers | jina-embeddings-v2-base-dejinaai/jina-embeddings-v2-base-de |
| Context window | 8,192 tokens Maximum input sequence in the model card; serving limits can be lower. Jina Embeddings v2 Base German-English model details |
| Parameters | 161 millionJina Embeddings v2 Base German-English model details |
| Weight license | Apache 2.0Jina Embeddings v2 Base German-English model details |
| Base model | JinaBERTJina Embeddings v2 Base German-English model details |
Related models
- Jina Embeddings v3
Jina AI · Jina Embeddings v3
A multilingual text model with separate query and passage adapters.
Launch date API · Downloadable - Jina Embeddings v2 Small English
Jina AI · Jina Embeddings v2
A 33-million-parameter English encoder with long-document input.
Launch date Downloadable