Update README.md

README.md

@@ -4,12 +4,12 @@ license: cc-by-nc-3.0
 
 PragS2: Pragmatic Masked Language Modeling with Emoji_any dataset followed by Hashtag-Based Surrogate Fine-Tuning
 
-You can load these model and use for downstream fine-tuning. For example:
+You can load this model and use for downstream fine-tuning. For example:
 ```python
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 
-tokenizer = AutoTokenizer.from_pretrained('UBC-NLP/prags1', use_fast = True)
-model = AutoModelForSequenceClassification.from_pretrained('UBC-NLP/prags1',num_labels=lable_size)
+tokenizer = AutoTokenizer.from_pretrained('UBC-NLP/prags2', use_fast = True)
+model = AutoModelForSequenceClassification.from_pretrained('UBC-NLP/prags2',num_labels=lable_size)
 ```