adding usage example

README.md

@@ -18,6 +18,13 @@ the publication of conference proceedings).
 The model has the bert-base architecture and configuration and was pretrained from scratch as a masked language model 
 on the Sanskrit reference corpus, and fine-tuned on the smaller corpus of Buddhist Sanskrit. 
 
+## How to use it
+
+```
+model = AutoModelForMaskedLM.from_pretrained("Matej/bert-base-buddhist-sanskrit")
+tokenizer = AutoTokenizer.from_pretrained("Matej/bert-base-buddhist-sanskrit", use_fast=True)
+```
+
 ## Intended uses & limitations
 
 MIT license, no limitations