Update app.py

app.py

@@ -1,7 +1,11 @@
 import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
 
-model = AutoModelForCausalLM.from_pretrained("ewernn/perfect-refusal-model")
+# Load base model
+base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct")
+# Load LoRA adapters on top
+model = PeftModel.from_pretrained(base_model, "ewernn/perfect-refusal-model")
 tokenizer = AutoTokenizer.from_pretrained("ewernn/perfect-refusal-model")
 
 def chat(message):