Update README.md

README.md

@@ -7,11 +7,7 @@ pipeline_tag: token-classification
 ---
 # bert-chunker-3
 
-
-## Introduction
-
-bert-chunker-3 is a text chunker based on BERT with a classifier head to predict the start token of chunks (for use in RAG, etc), and using a sliding window it cuts documents of any size into chunks. The training data are labeled by a LLM.
-
+bert-chunker-3 is a text chunker based on BERT with a classifier head to predict the start token of chunks (for use in RAG, etc), and using a sliding window it cuts documents of any size into chunks. Its training data are labeled by a LLM.
 
 ## Quickstart
 Run the following: