Update README.md

README.md

@@ -64,9 +64,7 @@ The model was trained on a POSMAC corpus. Polish Open Science Metadata Corpus (P
 
 # Tokenizer
 
-As in the original HerBERT implementation, the training dataset was tokenized into subwords using a character level byte-pair encoding (CharBPETokenizer) with a vocabulary size of 50k tokens. The tokenizer itself was trained with a tokenizers library.
-
-We kindly encourage you to use the Fast version of the tokenizer, namely HerbertTokenizerFast.
+As in the original plT5 implementation, the training dataset was tokenized into subwords using a sentencepiece unigram model with vocabulary size of 50k tokens. 
 
 # Usage