Update app.py

app.py

@@ -1,7 +1,7 @@
 import torch
 import gradio as gr
 import spaces
-from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
+from transformers import AutoModelForCausalLM, AutoTokenizer
 import os
 import re
 from polyglot.detect import Detector
@@ -12,13 +12,11 @@ RELATIVE_MODEL="LLaMAX/LLaMAX3-8B"
 
 TITLE = "<h1><center>LLaMAX3-Translator</center></h1>"
 
-quantization_config = BitsAndBytesConfig(load_in_8bit=True)
 
 model = AutoModelForCausalLM.from_pretrained(
         MODEL,
         torch_dtype=torch.float16,
-        device_map="auto",
-        quantization_config=quantization_config)
+        device_map="auto")
 tokenizer = AutoTokenizer.from_pretrained(MODEL)