Update app.py

app.py

@@ -12,11 +12,10 @@ tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
 model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path)
 
 # Load the Lora model
-model = PeftModel.from_pretrained(model, peft_model_id)
+model = PeftModel.from_pretrained(model, model_id)
 model.to(device)
 
-def greet(text
-):
+def greet(text):
     with torch.no_grad():  # Disable gradient calculation for inference
         batch = tokenizer(text, return_tensors='pt').to(device)  # Move tensors to device
         with torch.cuda.amp.autocast():  # Enable mixed-precision if available