Bilingual Embedding Base vs Bilingual Embedding Large
No benchmarks in this slice.
Specs
| Spec | Bilingual Embedding Base | Bilingual Embedding Large |
|---|---|---|
| Context | 1K | 1K |
| Weights | Open | Open |
| Released | Jun 2024 | Jun 2024 |
| Dimensions | 768 | 1,024 |
| Max input | 1K tokens | 1K tokens |
| Languages | — | en, fr |
| Memory (4-bit) | 0.2 GB | 0.3 GB |
| Licence | Apache-2.0 | Apache-2.0 |
| Commercial use | Allowed | Allowed |
What breaks when you switch
Bilingual Embedding Base → Bilingual Embedding Large
Re-embed your whole corpus›
Vectors from different models can't be mixed; dimensions change from 768 to 1,024.
Memory (4-bit): 0.2 GB → 0.3 GB
Bilingual Embedding Large → Bilingual Embedding Base
Re-embed your whole corpus›
Vectors from different models can't be mixed; dimensions change from 1,024 to 768.