Update README.md

README.md

@@ -57,7 +57,7 @@ You can run the smashed model with these steps:
       from transformers import AutoTokenizer, AutoModelForCausalLM
 
       tokenizer = AutoTokenizer.from_pretrained("PrunaAI/recurrentgemma-2b-bnb-4bit-smashed")
-      model = AutoModelForCausalLM.from_pretrained("PrunaAI/recurrentgemma-2b-bnb-4bit-smashed", device_map="auto")
+      model = AutoModelForCausalLM.from_pretrained("PrunaAI/recurrentgemma-2b-bnb-4bit-smashed")
       
       input_text = "Write me a poem about Machine Learning."
       input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")