Multilingual E5 Large vs Multilingual E5 Large Instruct
MTEB multilingual v2 · Mean over tasks · multilingual (1037 languages) Embeddings assign examples to categories, group similar examples, estimate semantic similarity between pairs, classify relationships between pairs, rank relevant documents for queries, find translated sentence pairs, rerank documents according to instructions, assign multiple labels to each example, reorder candidate documents by relevance on MTEB Multilingual v2 · mean over tasks in 1037 languages including 'Auhelawa, Abau, Achi, Achinese, Achuar-Shiwiar, Adzera, Afrikaans, Agarabi; tasks receive equal weight
Multilingual E5 Large—
Multilingual E5 Large Instruct63.2
| Benchmark | Multilingual E5 Large | Multilingual E5 Large Instruct |
|---|---|---|
| MTEB multilingual v2 · Mean over tasks · multilingual (1037 languages) | — | 63.2 |
Specs
| Spec | Multilingual E5 Large | Multilingual E5 Large Instruct |
|---|---|---|
| Price | !$0.01 | !$0.01 |
| Context | 1K | 1K |
| Weights | Open | Open |
| Released | Feb 2024 | Feb 2024 |
| Dimensions | 1,024 | 1,024 |
| Max input | 1K tokens | 1K tokens |
| Languages | en, Esperanto, es +90 | en, Esperanto, es +90 |
| Memory (4-bit) | 0.3 GB | 0.3 GB |
| Licence | MIT | MIT |
| Commercial use | Allowed | Allowed |
What breaks when you switch
Multilingual E5 Large → Multilingual E5 Large Instruct
Re-embed your whole corpus›
Vectors from different models can't be mixed.
Multilingual E5 Large Instruct → Multilingual E5 Large
Re-embed your whole corpus›
Vectors from different models can't be mixed.