Update app.py

app.py

@@ -1,16 +1,16 @@
-from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 import gradio as gr
 import spaces
 import torch
 import re
+import json
+import os
+import time
+import threading
 from threading import Thread
 from typing import Iterator
 from datetime import datetime
 from huggingface_hub import HfApi, hf_hub_download
-import json
-import os
-import time
-
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 model_name = "Woziii/llama-3-8b-chat-me"
 model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype=torch.float16)
 tokenizer = AutoTokenizer.from_pretrained(model_name)