Update app.py

app.py

@@ -7,6 +7,7 @@ import gradio as gr
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
 from bitsandbytes.functional import quantize_blockwise
+from bitsandbytes.nn import Linear4bit
 
 tokenizer = AutoTokenizer.from_pretrained("FlawedLLM/Bhashini_gemma_merged4bit_clean_final")
 model = AutoModelForCausalLM.from_pretrained("FlawedLLM/Bhashini_gemma_merged4bit_clean_final")