alibaba / alibaba/ROLL

qwen3-omni 是否支持视频输入?如果支持数据集格式应该是什么样的?

Open
#362 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
3.4k
Forks
312
Avg merge
1h 2m
Merged PRs (30d)
2

Description

example中qwen3-omni只包含rlvr 的脚本,agentic pipeline是否支持?

Contributor guide

No contributing guide indexed for this repository

Research direction

Start with the qwen3-omni example and its RLVR scripts, then trace the agentic pipeline entry point to determine whether video inputs are supported. Check the existing dataset schema used by the example. Done should be a maintainer-confirmed answer or a clearly scoped documentation task covering video support and dataset format.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.