Mmlw E5 Base vs Mmlw Roberta Base
Mmlw E5 Base44.2
Mmlw Roberta Base41.5
| Benchmark | Mmlw E5 Base | Mmlw Roberta Base |
|---|---|---|
| MTEB multilingual v2 · Mean over tasks · multilingual (1037 languages) | 44.2 | 41.5 |
Specs
| Spec | Mmlw E5 Base | Mmlw Roberta Base |
|---|---|---|
| Context | 1K | 1K |
| Weights | Open | Open |
| Released | Nov 2023 | Nov 2023 |
| Dimensions | 768 | 768 |
| Max input | 1K tokens | 1K tokens |
| Languages | Polish | Polish |
| Memory (4-bit) | 0.2 GB | 0.1 GB |
| Licence | Apache-2.0 | Apache-2.0 |
| Commercial use | Allowed | Allowed |
What breaks when you switch
Mmlw E5 Base → Mmlw Roberta Base
Re-embed your whole corpus›
Vectors from different models can't be mixed.
Mmlw Roberta Base → Mmlw E5 Base
Re-embed your whole corpus›
Vectors from different models can't be mixed.