Update README.md

README.md

@@ -54,11 +54,13 @@ model = GPT2LMHeadModel.from_pretrained(path_to_folder_with_checkpoint_files)
 You should first pretokenize your text using the [MosesTokenizer](https://pypi.org/project/mosestokenizer/):
 
 ```python
+from mosestokenizer import MosesTokenizer
+
 with MosesTokenizer('en') as pretokenize:
     pretokenized_text = " ".join(pretokenize(text_string))
 ```
 
-To tokenize your text for this model, you should use the [tokenizer trained on Wikitext-103](https://huggingface.co/Kristijan/wikitext-103-tokenizer_v2):
+Then, to BPE tokenize your text for this model, you should use the [tokenizer trained on Wikitext-103](https://huggingface.co/Kristijan/wikitext-103-tokenizer_v2):
 
 ```python
 from transformers import GPT2TokenizerFast