Update app.py

app.py

@@ -1,5 +1,6 @@
-from transformers import MllamaForConditionalGeneration, AutoProcessor, TextIteratorStreamer
+from transformers import MllamaForConditionalGeneration, AutoProcessor, AutoTokenizer, TextIteratorStreamer, AutoModelForCasualLM
 from PIL import Image
+import os
 import requests
 import torch
 from threading import Thread
@@ -7,11 +8,17 @@ import gradio as gr
 from gradio import FileData
 import time
 import spaces
+
+
+hf_token = os.environ.get("HGHugging")
+
 ckpt = "meta-llama/Llama-3.2-11B-Vision-Instruct"
+
 model = MllamaForConditionalGeneration.from_pretrained(ckpt,
     torch_dtype=torch.bfloat16).to("cuda")
 processor = AutoProcessor.from_pretrained(ckpt)
-tokenizer = AutoTokenizer.from_pretrained( "meta-llama/Llama-3.2-11B-Vision-Instruct", token=HGHugging )
+tokenizer = AutoTokenizer.from_pretrained( "meta-llama/Llama-3.2-11B-Vision-Instruct", token=hf_token )
+
 
 @spaces.GPU
 def bot_streaming(message, history, max_new_tokens=250):