Update app.py

app.py

@@ -1,5 +1,6 @@
 import gradio as gr
-from peft import PeftModel, PeftConfig
+from peft import
+ PeftModel, PeftConfig
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 
@@ -14,7 +15,6 @@ model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path)
 
 # Load the Lora model
 model = PeftModel.from_pretrained(model, model_id)
-model.to(device)
 
 def greet(text):
     with torch.no_grad():  # Disable gradient calculation for inference