Update readme

README.md

@@ -8648,3 +8648,8 @@ model-index:
     - type: similarity_recall
       value: 84.02371419772098
 ---
+
+
+<h2 align="center"> LENS Embeddings</h2>
+
+LENS is a model that produces **L**exicon-based **E**mbeddi**N**g**S** (LENS) leveraging large language models. Each dimension of the embeddings is designed to correspond to a token cluster where semantically similar tokens are grouped together. These embeddings have a similar feature size as dense embeddings, with LENS-d8000 offering 8000-dimensional representations.