Update app.py

app.py

@@ -6,9 +6,11 @@ import spaces
 import gradio as gr
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
+from bitsandbytes.functional import quantize_blockwise
 
 tokenizer = AutoTokenizer.from_pretrained("FlawedLLM/Bhashini_gemma_merged4bit_clean_final")
 model = AutoModelForCausalLM.from_pretrained("FlawedLLM/Bhashini_gemma_merged4bit_clean_final")
+model= quantize_blockwise(model)
 # alpaca_prompt = You MUST copy from above!
 @spaces.GPU(duration=300)
 def chunk_it(input_command, item_list):