Paraphrase Multilingual MPNet
Specifications
- Input
- Output
- Context window
- 128 tokens
- Released
- Jun 2021
Performance
- Speed
- 435 t/s
- TTFT
- —
- Latency
- 278 ms
- Intelligence
- —
Pricing
- Input
- €0.01 per 1M tokens
- Output
- €0.00 per 1M tokens
About this model
Sentence Transformers Paraphrase Multilingual MPNet is a multilingual sentence embedding model based on MPNet architecture, supporting 50+ languages for cross-lingual semantic similarity and paraphrase detection. Trained on large-scale paraphrase datasets across multiple languages enabling strong cross-lingual transfer. Ideal for multilingual paraphrase detection, semantic textual similarity, cross-lingual search, and international content deduplication. Provides balanced performance across diverse language families with proven track record in sentence-transformers ecosystem.
Technical specifications
- Capabilities
- Input modalities
- Output modalities
- Reasoning
- No
Knowledge horizon
Released Jun 2021
Today
Since release 60 mo
See also
Add Model to Comparison
Search for a model to add