Update app.py

app.py

@@ -3,6 +3,7 @@ import gradio as gr
 import transformers
 from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 import torch
+import os
 
 title = """
 # Welcome to 🌟Tonic's🫡Command-R
@@ -24,6 +25,7 @@ model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_c
 
 @spaces.GPU
 def generate_response(user_input, max_new_tokens, temperature):
+    os.system('nvidia-smi')
     messages = [{"role": "user", "content": user_input}]
     input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
     input_ids = input_ids.to(model.device)