Update README.md

README.md

@@ -22,7 +22,7 @@ All the models have a comparable model size between 90 MB and 150 MB, BPE tokeni
 
 ### Architecture
 
-The model is trained based on the InstaDeepAI/nucleotide-transformer-v2-100m-multi-species model with modified tokenizer that replaces k-mer to BPE.
+The model is trained based on the InstaDeepAI/nucleotide-transformer-v2-100m-multi-species model.
 
 This model is fine-tuned for predicting open chromatin.