NVIDIA-NeMo / NVIDIA-NeMo/Automodel
Support vlm training with multi-image and videos
Open
@HuiyingLi is already working on this.
Since Mar 5, 2026.
enhancement
- Dominant language
- Python
- Stars
- 963
- Forks
- 318
- Avg merge
- 3d 20h
- Merged PRs (30d)
- 143
Description
Dataset format that supports mixtures of pure text, single/multi image and video
e.g. jsonls
{
"conversations": [
{"from": "human", "value": "\nDescribe first. \nNow second."},
{"from": "gpt", "value": "First is... Second is..."}
],
"images": ["img1.jpg", "img2.jpg"]
}
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.