Update app.py

app.py

@@ -1,8 +1,11 @@
 import gradio as gr
 import torch
+from transformers import BitsAndBytesConfig
 from transformers import AutoModelForCausalLM, AutoTokenizer
 from transformers import StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer
 from threading import Thread
+import bitsandbytes
+
 
 # Loading the tokenizer and model from Hugging Face's model hub.
 tokenizer = AutoTokenizer.from_pretrained("CohereForAI/c4ai-command-r-v01-4bit")