Update README.md

README.md

@@ -38,7 +38,7 @@ pip install transformers torch sentencepiece
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-device = "cuda" # change to cpu if you have no gpu
+device = "cpu" # change to cuda if you want to use the gpu and have cuda installed
 
 model = AutoModelForCausalLM.from_pretrained("MoxoffSpA/Azzurro")
 tokenizer = AutoTokenizer.from_pretrained("MoxoffSpA/Azzurro")
@@ -59,7 +59,7 @@ encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
 model_inputs = encodeds.to(device)
 model.to(device)
 
-generated_ids = model.generate(model_inputs, max_new_tokens=250, do_sample=True)
+generated_ids = model.generate(model_inputs, max_new_tokens=256, do_sample=True)
 decoded = tokenizer.batch_decode(generated_ids)
 print(decoded[0])
 ```