Update app.py

app.py

@@ -2,15 +2,11 @@ import os
 import bitsandbytes as bnb
 import torch
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+from transformers import AutoTokenizer, AutoModelForCausalLM, HqqConfig
 
 access_token = os.environ["GATED_ACCESS_TOKEN"]
 
-quantization_config = BitsAndBytesConfig(
-        load_in_4bit=True,
-        bnb_4bit_quant_type="nf4",
-        bnb_4bit_compute_dtype="float16",
-)
+quantization_config = HqqConfig()
 
 model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1", quantization_config=quantization_config, device_map="auto", token=access_token)
 tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1")