diff --git a/README.md b/README.md
index da84c972a..794f1352b 100644
--- a/README.md
+++ b/README.md
@@ -53,12 +53,13 @@ You can use our Hugging Face integration to run inference on the OLMo Transforme
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
-
 olmo = AutoModelForCausalLM.from_pretrained("allenai/OLMo-2-1124-7B")
 tokenizer = AutoTokenizer.from_pretrained("allenai/OLMo-2-1124-7B")
-
 message = ["Language modeling is "]
 inputs = tokenizer(message, return_tensors='pt', return_token_type_ids=False)
+# optional verifying cuda
+# inputs = {k: v.to('cuda') for k,v in inputs.items()}
+# olmo = olmo.to('cuda')
 response = olmo.generate(**inputs, max_new_tokens=100, do_sample=True, top_k=50, top_p=0.95)
 print(tokenizer.batch_decode(response, skip_special_tokens=True)[0])
 ```