Replies: 1 comment
-
|
目前MinerU官方没有提供现成的微调脚本或详细文档,但MinerU2___5-2509-1___2B(VLM)模型本身兼容Huggingface生态,可以用标准的Huggingface工具进行微调。大致流程如下:
详细讨论和社区经验可参考:GitHub Discussions 4002 和 3191。 目前没有官方数据集模板或自动化脚本,需参考Huggingface多模态任务的通用做法自行实现。微调时请确保数据标注准确,格式规范,并遵循Huggingface最佳实践。 To reply, just mention @dosu. How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
你好,我当前打算使用vlm模型识别工件图纸,但是mineru模型在识别(分割)其中的图片的时候会存在一些细微的偏差,请问我该(在哪里查看)如何设置自己的数据集去实现vlm模型的微调?
Beta Was this translation helpful? Give feedback.
All reactions