Bge Large En v1.5 vs Bge Small En v1.5
Bge Large En v1.545.1
Bge Small En v1.543.8
| Benchmark | Bge Large En v1.5 | Bge Small En v1.5 |
|---|---|---|
| MTEB multilingual v2 · Mean over tasks · multilingual (1037 languages) | 45.1 | 43.8 |
Specs
| Spec | Bge Large En v1.5 | Bge Small En v1.5 |
|---|---|---|
| Price | !$0.01 | !$0.02 |
| Context | 1K | 1K |
| Weights | Open | Open |
| Released | Sep 2023 | Sep 2023 |
| Dimensions | 1,024 | 384 |
| Max input | 1K tokens | 1K tokens |
| Languages | en | en |
| Memory (4-bit) | 0.2 GB | 0 GB |
| Licence | MIT | MIT |
| Commercial use | Allowed | Allowed |
What breaks when you switch
Bge Large En v1.5 → Bge Small En v1.5
Re-embed your whole corpus›
Vectors from different models can't be mixed; dimensions change from 1,024 to 384.
Bge Small En v1.5 → Bge Large En v1.5
Re-embed your whole corpus›
Vectors from different models can't be mixed; dimensions change from 384 to 1,024.