Update README.md

README.md

@@ -13,7 +13,7 @@ language:
 
 # thehosy/roberta-base-qa-vietnamese
 
-This is a encoder model: It can encodes sentences or paragraphs (maximum 768 tokens) to dense vectors with 760 dimensions. It used for QA semantic search.
+This is a encoder model: It can encodes sentences or paragraphs (maximum 768 tokens) to dense vectors with 768 dimensions. It used for QA semantic search.
 
 Datasets: 
   - MS Macro (translated into Vietnamese)
@@ -30,7 +30,7 @@ Roberta-base architecture is used as backbone (Training from scratch).
 Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
 
 ```
-pip install -U sentence-transformers
+pip install -q sentence-transformers
 ```
 
 Then you can use the model like this: