Update README.md

README.md

@@ -149,11 +149,11 @@ The comparison reveals several key differences between ELN and standard training
 ## Usage
 
 ```python
-from peft import PeftModel
-from transformers import AutoModelForCausalLM
+# Load model directly
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
-base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-1B")
-model = PeftModel.from_pretrained(base_model, "diabolic6045/ELN-llama-1B-adapter")
+tokenizer = AutoTokenizer.from_pretrained("diabolic6045/ELN-Llama-1B")
+model = AutoModelForCausalLM.from_pretrained("diabolic6045/ELN-Llama-1B")
 ```
 
 ## Framework Versions