FremyCompany commited on
Commit
5128271
·
verified ·
1 Parent(s): bbcca5b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ library_name: sentence-transformers
22
 
23
  # FMMB-BE-DE: The Fairly Multilingual ModernBERT Embedding Model (Belgian Edition): Monolingual German version.
24
 
25
- 🇳🇱 This monolingual German version of the [Fairly Multilingual ModernBERT Embedding Model (Belgian Edition)](https://huggingface.co/Parallia/Fairly-Multilingual-ModernBERT-Embed-BE) is the perfect model for embedding texts up to 8192 tokens written in German at the speed of light. It uses the exact same weights as the original FMMB-BE model, and therefore produces identical embeddings, but this version comes with only a German-optimized tokenizer and its associated embedding table, thereby improving performance.
26
 
27
  🆘 This [sentence-transformers](https://www.SBERT.net) model was trained on a small parallel corpus containing English-French, English-Dutch, and English-German sentence pairs. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. The input texts can be used as-is, no need to use prefixes.
28
 
 
22
 
23
  # FMMB-BE-DE: The Fairly Multilingual ModernBERT Embedding Model (Belgian Edition): Monolingual German version.
24
 
25
+ 🇩🇪 This monolingual German version of the [Fairly Multilingual ModernBERT Embedding Model (Belgian Edition)](https://huggingface.co/Parallia/Fairly-Multilingual-ModernBERT-Embed-BE) is the perfect model for embedding texts up to 8192 tokens written in German at the speed of light. It uses the exact same weights as the original FMMB-BE model, and therefore produces identical embeddings, but this version comes with only a German-optimized tokenizer and its associated embedding table, thereby improving performance.
26
 
27
  🆘 This [sentence-transformers](https://www.SBERT.net) model was trained on a small parallel corpus containing English-French, English-Dutch, and English-German sentence pairs. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. The input texts can be used as-is, no need to use prefixes.
28