Add load_in_4bit flag for base model

README.md

@@ -44,7 +44,7 @@ To use these weights:
 from peft import PeftModel, PeftConfig
 from transformers import AutoModelForCausalLM
 
-config = PeftConfig.from_pretrained("arnavgrg/codealpaca-qlora")
+config = PeftConfig.from_pretrained("arnavgrg/codealpaca-qlora", load_in_4bit=True)
 model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf")
 model = PeftModel.from_pretrained(model, "arnavgrg/codealpaca-qlora")
 ```