Update app.py

app.py

@@ -14,10 +14,11 @@ 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
-        batch = tokenizer(text, return_tensors='pt').to(device)  # Move tensors to device
+        batch = tokenizer(f'"{text}" ->:', return_tensors='pt').to(device)  # Move tensors to device
         with torch.cuda.amp.autocast():  # Enable mixed-precision if available
             output_tokens = model.generate(**batch, max_new_tokens=15)
     return tokenizer.decode(output_tokens[0], skip_special_tokens=True)