请问R1V2中的MPO数据集是如何构造的呢

Open
#24 5 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
15/100
Issue type
Documentation
Clarity
Needs clarification
Activity status
Stale
Tech stack
machine-learning, python
Domain
data, machine-learning

Research direction

No files, tests, or entry points are identified in the issue. First locate the documentation or dataset-construction materials for MPO, MMPR, and the Skywork-VL reward model, then confirm whether they answer the three questions about data composition, reasoning traces, and chosen/rejected samples.

Written by the indexing model from the issue text.

Description

很不错的工作，关于文中的MPO，有几个问题想请教一下：
1、数据是MMPR数据集还是另外构造的呢，具体构成是什么样的呢
2、MPO用的数据集是带思考过程的吗
3、Skywork-VL reward model是用于构造chosen和reject的吗

Dominant language
Python
Stars
3.2k
Forks
282
No merged PRs in 30d

Contributor guide

No contributing guide indexed for this repository

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.

More from SkyworkAI/Skywork-R1V

All issues in SkyworkAI/Skywork-R1V

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.