Update app.py

app.py

@@ -1,14 +1,14 @@
 import gradio as gr
 from peft import AutoPeftModelForCausalLM
-from transformers import AutoTokenizer
+from transformers import AutoTokenizer, BitsAndBytesConfig
 import torch
 
 # Load the model and tokenizer
 model_name = "ahmedembedded/AskFAST"
-load_in_4bit = True
+quantization_config = BitsAndBytesConfig(load_in_4bit=True)
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
-model = AutoPeftModelForCausalLM.from_pretrained(model_name, load_in_4bit=load_in_4bit).to(device)
+model = AutoPeftModelForCausalLM.from_pretrained(model_name, quantization_config=quantization_config).to(device)
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 
 # Define the prompt context