video processing code failed

the code of processing video code is as
https://github.com/DAMO-NLP-SG/VideoLLaMA3/blob/22a53e317e057306adce199094bc9956904101de/videollama3/train.py#L248

It is inconsistent with the instructions to build dataset in readme file. In reademe file , the "video" is not a list but a string object.
```

[
{
"video": "images/xxx.jpg",
"conversations": [
{
"from": "human",
"value": "\nWhat are the colors of the bus in the image?"
},
{
"from": "gpt",
"value": "The bus in the image is white and red."
},
...
],
}
{
"video": "videos/xxx.mp4",
"conversations": [
{
"from": "human",
"value": "\nWhat are the main activities that take place in the video?"
},
{
"from": "gpt",
"value": "The main activities that take place in the video are the preparation of camera equipment by a man, a group of men riding a helicopter, and a man sailing a boat through the water."
},
...
],
},
...
]
```

Compare the dataset handling at train.py line 248 with the dataset format shown in the README, focusing on whether the video field is treated as a string or a list. Confirm the expected format for both image and video entries, then verify that the implementation and README describe the same structure.

Written by the indexing model from the issue text.