NVIDIA-NeMo / NVIDIA-NeMo/Automodel

Support vlm training with multi-image and videos

Open
#1,460 0 comments 0 reactions 1 assignee View on GitHub

@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

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.