Update README.md

README.md

@@ -142,7 +142,7 @@ You'll find different techniques for running inference, including Huggingface's
 The Huggingface Text Generation Pipeline provides a straightforward way to run inference using the Salamandra-7b model.
 
 ```bash
-pip install -U transformers
+pip install transformers torch accelerate sentencepiece protobuf
 ```
 <details>
 <summary>Show code</summary>