Update README.md

README.md

@@ -27,7 +27,7 @@ With huggingface transformers you only need to be a bit careful with how you poo
 ```python
 from transformers import AutoTokenizer, AutoModel
 
-pooler = lambda x: x[:, 0, :] # Choose CLS token and normalize
+pooler = lambda x: x[:, 0, :] # Choose CLS token
 
 sentences = ["This is an example sentence", "Each sentence is converted"]
 tokenizer = AutoTokenizer.from_pretrained('quicktensor/dexml_lf-amazontitles-1.3m')