Update app.py

app.py

@@ -15,7 +15,7 @@ tokenizer = AutoTokenizer.from_pretrained("vikhyatk/moondream2")
 moondream = AutoModelForCausalLM.from_pretrained(
     "vikhyatk/moondream-next", trust_remote_code=True,
     torch_dtype=torch.bfloat16, device_map={"": "cuda"},
-    attn_implementation="flash_attention_2"
+    attn_implementation="flash_attention_2", use_auth_token=auth_token
 )
 moondream.eval()