Bge Base En v1.5 vs Bge Large En v1.5
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
Bge Base En v1.544.5
Bge Large En v1.545.1
| Benchmark | Bge Base En v1.5 | Bge Large En v1.5 |
|---|---|---|
| MTEB multilingual v2 · Mean over tasks · multilingual (1037 languages) | 44.5 | 45.1 |
Specs
| Spec | Bge Base En v1.5 | Bge Large En v1.5 |
|---|---|---|
| Price | !$0.005 | !$0.01 |
| Context | 1K | 1K |
| Weights | Open | Open |
| Released | Sep 2023 | Sep 2023 |
| Dimensions | 768 | 1,024 |
| Max input | 1K tokens | 1K tokens |
| Languages | en | en |
| Memory (4-bit) | 0.1 GB | 0.2 GB |
| Licence | MIT | MIT |
| Commercial use | Allowed | Allowed |
What breaks when you switch
Bge Base En v1.5 → Bge Large En v1.5
Re-embed your whole corpus›
Vectors from different models can't be mixed; dimensions change from 768 to 1,024.
Memory (4-bit): 0.1 GB → 0.2 GB
Bge Large En v1.5 → Bge Base En v1.5
Re-embed your whole corpus›
Vectors from different models can't be mixed; dimensions change from 1,024 to 768.