Update README.md

README.md

@@ -13,7 +13,9 @@ tags:
 
 This is a truncated version of [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2).
 
-This model has only English and Russian tokens left in the vocabulary. It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+This model has only English and Russian tokens left in the vocabulary. Thus making it twice as small as the original model while producing the same embeddings.
+
+Model maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
 
 
 ## Usage (Sentence-Transformers)