Update README.md

README.md

@@ -21,7 +21,6 @@ An extensive dataset with “artificial” errors was taken as a training corpus
 - [SAGE library announcement](https://youtu.be/yFfkV0Qjuu0), DataFest 2023
 - [Paper about synthetic error generation methods](https://www.dialog-21.ru/media/5914/martynovnplusetal056.pdf), Dialogue 2023
 - [Paper about SAGE and our best solution](https://arxiv.org/abs/2308.09435), Review EACL 2024
-- Path to model = "ai-forever/T5-large-spell"
 
 ### Examples
 | Input | Output |
@@ -61,14 +60,14 @@ We present a comparison of our solution both with open automatic spell checkers
 ```python
 from transformers import T5ForConditionalGeneration, AutoTokenizer
 
-path_to_model = "<path_to_model>"
+path_to_model = "ai-forever/T5-large-spell"
 
 model = T5ForConditionalGeneration.from_pretrained(path_to_model)
 tokenizer = AutoTokenizer.from_pretrained(path_to_model)
 prefix = "grammar: "
 
 sentence = "If you bought something goregous, you well be very happy."
-sentence = prefix + grammar
+sentence = prefix + sentence
 
 encodings = tokenizer(sentence, return_tensors="pt")
 generated_tokens = model.generate(**encodings)