Update app.py

app.py

@@ -836,7 +836,7 @@ if __name__ == "__main__":
         # torch_dtype=args.torch_dtype,
         attn_implementation='sdpa',  # OR 'sdpa' for Ascend NPUs
         low_cpu_mem_usage=True,
-        trust_remote_code=True).eval().cuda()
+        trust_remote_code=True).eval().to(torch.bfloat16).cuda()
     processor = AutoProcessor.from_pretrained(args.model_name, trust_remote_code=True)
 
     # set the vision tokenizer for decoding image.