Update app.py

app.py

@@ -1,13 +1,14 @@
 import spaces
 import gradio as gr
 import transformers
-from transformers import AutoTokenizer, AutoModelForCausalLM
+from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 import torch
 
-# Load the tokenizer and model
+bnb_config = BitsAndBytesConfig(load_in_8bit=True)
+
 model_id = "CohereForAI/c4ai-command-r-v01"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config)
 
 @spaces.GPU
 def generate_response(user_input, max_new_tokens, temperature):