GRPO下的多轮多模态对话数据集构建 #4118

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Open

Weep-ing-Angel opened this issue May 7, 2025 · 0 comments

Labels

Weep-ing-Angel commented May 7, 2025

您好，目前我想进行多模态的多轮对话的GRPO训练，我在构建数据集时遇到了一些困难。

我目前构建的数据结构如下：

我第一轮对话需要输入两张图像，第二轮对话是一张图像的grounding
这样的数据集模型只会生成最后一轮的assistant吧，我应该如何去实现多轮的一个生成？

我能否将第二轮的query和image通过其他字段传入（而非“messages”），从而通过multi_turn_func实现第二轮对话？

hjh0119 added the enhancement label

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment