Update README.md

README.md

@@ -9,7 +9,7 @@ language:
 
 A really tiny sentence reranker (models use only 120mb) that runs almost instantly on cpu.
 
-Trained using a mix of embeddings from wordllama and hashingvectorizer, on a dataset based on msmarco.
+Trained using a mix of embeddings from universal-sentence-encoder and hashingvectorizer, on a dataset based on msmarco.
 
 *   pip install nanoranker