Update app.py

app.py

@@ -7,11 +7,18 @@ import gradio as gr
 from gradio import FileData
 import time
 import spaces
+import os
+from huggingface_hub import InferenceClient
+
+
 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)
 
+token = os.getenv('deepseekv2')
+client = InferenceClient(model, token=os.getenv('deepseekv2'))
+
 
 @spaces.GPU
 def bot_streaming(message, history, max_new_tokens=250):