Update README.md

README.md

@@ -40,6 +40,10 @@ The model performs exceptionally well on writing, explanation and discussion tas
 
 
 ## Use in 🤗Transformers
+First install direct dependencies:
+```
+pip install transformers torch sentencepiece
+```
 If you want faster inference using flash-attention2, you need to install these dependencies:
 ```bash
 pip install packaging ninja