Update README.md

README.md

@@ -29,7 +29,7 @@ We evaluated the model using the same test sets as used for the Open Ita LLM Lea
 
 ## Usage
 
-Be sure to have transformers and torch installed
+Be sure to install these dependecies before running the program
 
 ```python
 pip install transformers torch sentencepiece
@@ -38,7 +38,7 @@ pip install transformers torch sentencepiece
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-device = "cpu" # change to cuda if you want to use the gpu and have cuda installed
+device = "cpu" # if you want to use the gpu make sure to have cuda toolkit installed and change this to "cuda"
 
 model = AutoModelForCausalLM.from_pretrained("MoxoffSpA/Azzurro")
 tokenizer = AutoTokenizer.from_pretrained("MoxoffSpA/Azzurro")