Update README.md

README.md

@@ -3,12 +3,10 @@ library_name: transformers
 tags: []
 ---
 
-# LLM2Vec
+# LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
 
-> 2 line summary of our contribution
->
-- **Repository:** 
-- **Paper:** 
+> LLM2Vec is a simple recipe to convert decoder-only LLMs into text encoders. It consists of 3 simple steps: 1) enabling bidirectional attention, 2) masked next token prediction, and 3) unsupervised contrastive learning. The model can be further fine-tuned to achieve state-of-the-art performance.
+- **Repository:** https://github.com/McGill-NLP/llm2vec
 
 
 ## Installation
@@ -60,5 +58,3 @@ cos_sim = torch.mm(q_reps_norm, d_reps_norm.transpose(0, 1))
 print(cos_sim.tolist())
 
 ```
-
-## Citation