Update app.py

app.py

@@ -2,7 +2,7 @@ import torch
 from PIL import Image
 import gradio as gr
 import spaces
-from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+from transformers import AutoModelForCausalLM, AutoTokenizer, Qwen2Tokenizer, TextIteratorStreamer
 import os
 from threading import Thread
 
@@ -41,7 +41,7 @@ model = AutoModelForCausalLM.from_pretrained(
           torch_dtype=torch.float16,
           device_map="auto",
         )
-tokenizer = AutoTokenizer.from_pretrained(MODELS)
+tokenizer = Qwen2Tokenizer.from_pretrained(MODELS)
 
 @spaces.GPU
 def stream_chat(message: str, history: list, temperature: float, max_new_tokens: int, top_p: float, top_k: int, penalty: float):