Update README.md

README.md

@@ -17,12 +17,10 @@ This was trained as part of the paper [RomanSetu: Efficiently unlocking multilin
 The codebase used to train and evaluate this model can be found at [https://github.com/AI4Bharat/romansetu](https://github.com/AI4Bharat/romansetu).
 
 ## Usage
-Clone [https://github.com/AI4Bharat/romansetu](https://github.com/AI4Bharat/romansetu) and install the required dependencies. Then download or clone this model to the same machine.
-
-## Example
 
 ```python3
 from transformers import AutoTokenizer, AutoModelForCausalLM
 model_path = "ai4bharat/romansetu-cpt-roman-400m"
 tokenizer = AutoTokenizer.from_pretrained(model_path)
-model = AutoModelForCausalLM.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(model_path)
+```