Update README.md

README.md

@@ -11,7 +11,7 @@ The **miCSE** language model is trained for sentence similarity computation. Tra
 
 
 # Intended Use
-The model intended to be used for encoding sentences or short paragraphs. Given an input text, the model produces a vector embedding, which captures the semantics. The embedding can be used for numerous tasks, e.g., retrieval, clustering or sentence similarity comparison.
+The model intended to be used for encoding sentences or short paragraphs. Given an input text, the model produces a vector embedding, which captures the semantics. The embedding can be used for numerous tasks, e.g., **retrieval**, **clustering** or **sentence similarity** comparison (see example below).
 
 
 # Model Usage
@@ -64,7 +64,7 @@ print(f"Distance: {cos_sim[0,1].detach().item()}")
 
 # Training data
 
-The model was trained on a random collection of sentences from Wikipedia: [Training data file](https://huggingface.co/datasets/princeton-nlp/datasets-for-simcse/resolve/main/wiki1m_for_simcse.txt)
+The model was trained on a random collection of **English** sentences from Wikipedia: [Training data file](https://huggingface.co/datasets/princeton-nlp/datasets-for-simcse/resolve/main/wiki1m_for_simcse.txt)
 
 # Benchmark