From df2017862938c669f30810012a03de6a54b120f9 Mon Sep 17 00:00:00 2001
From: Parishad BehnamGhader <parishad.behnamghader@mila.quebec>
Date: Thu, 4 Apr 2024 16:11:58 -0400
Subject: [PATCH] Update README.md

---
 README.md | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/README.md b/README.md
index 7051142..3ea5c6c 100644
--- a/README.md
+++ b/README.md
@@ -1,12 +1,11 @@
-# LLM2Vec
-
-*LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders*. 
+# *LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders* 
+LLM2Vec is a simple recipe to convert decoder-only LLMs into text encoders. It consists of 3 simple steps: 1) enabling bidirectional attention, 2) training with masked next token prediction, and 3) unsupervised contrastive learning. The model can be further fine-tuned to achieve state-of-the-art performance.
 
 <p align="center">
   <img src="https://github.com/McGill-NLP/llm2vec/assets/12207571/48efd48a-431b-4625-8e0f-248a442e3839" width="75%" alt="LLM2Vec_figure1"/>
 </p>
 
-## Instrallation
+## Installation
 To use LLM2Vec, first install the llm2vec package from PyPI.
 
 ```bash