Model Name | paraphrase-multilingual-mpnet-base-v2 |
Description | A good general model to deal with multilingual data |
Use For | Text of multiple languages |
Limitations | Text longer than 512 tokens will be truncated |
Graft Default | No |
Reference information
Source | paraphrase-multilingual-mpnet-base-v2 - hugging face |
Trained on | Paraphrase datasets |
Paper | Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation |
Embedding Dimension | 768 |