Update README.md

README.md

@@ -2,6 +2,27 @@ A monolingual T5 model for Persian trained on OSCAR 21.09 (https://oscar-corpus.
 
 It's similar to the English T5 model but just for Persian. You may need to fine-tune it on your specific task. 
 
+Example code:
+
+```
+from transformers import T5ForConditionalGeneration,AutoTokenizer
+
+import torch
+
+model_name = "Ahmad/parsT5-base"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = T5ForConditionalGeneration.from_pretrained(model_name)
+
+input_ids = tokenizer.encode('دانش آموزان به <extra_id_0> میروند و <extra_id_1> میخوانند.', return_tensors='pt')
+with torch.no_grad():
+    hypotheses = model.generate(input_ids)
+for h in hypotheses:
+    print(tokenizer.decode(h))
+```
+
+
+
+
 Steps: 725000
 
 Accuracy: 0.66