update model card

README.md

@@ -27,10 +27,10 @@ Additional information about this model:
 The model can be loaded to perform a few-shot classification like so:
 
 ```py
-from transformers import AutoModelForConditionalGeneration, AutoTokenizer
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
 
-AutoModelForConditionalGeneration.from_pretrained("jpelhaw/t5-word-sense-disambiguation")
-AutoTokenizer("jpelhaw/t5-word-sense-disambiguation")
+AutoModelForSeq2SeqLM.from_pretrained("jpelhaw/t5-word-sense-disambiguation")
+AutoTokenizer.from_pretrained("jpelhaw/t5-word-sense-disambiguation")
 
 input = 'question: which description describes the word " peculiarities " best in the following context? \
   descriptions: [  " an odd or unusual characteristic " ,  " a distinguishing trait " ,  or " something unusual -- perhaps worthy of collecting " ] \