Update README.md

README.md

@@ -12,13 +12,13 @@ For Semantic Search Applications<br/>
 UForm is a Multi-Modal Modal Inference package, designed to encode Multi-Lingual Texts, Images, and, soon, Audio, Video, and Documents, into a shared vector space!
 It extends the `transfromers` package to support Mid-fusion Models.
 
-This is model card of __English only model__ with:
+This is model card of the __English only model__ with:
 
 * 4 layers BERT (2 layers for unimodal encoding and rest layers for multimodal encoding)
 * ViT-B/16 (image resolution is 224x224)
 
 
-If you need multilingual model, check [this](https://huggingface.co/unum-cloud/uform-vl-multilingual).
+If you need Multilingual model, check [this](https://huggingface.co/unum-cloud/uform-vl-multilingual).
 
 ## Installation