InternLM / InternLM/InternLM-XComposer
train模式和test模式差别很大
Open
- Dominant language
- Python
- Stars
- 2.9k
- Forks
- 175
- PR merge metrics
- No merged PRs in 30d
Description
我对一张图片微调至过拟合，训练过程中生成的答案与真值已经完全相同，但是我加载此模型去测试同一张图发现，生成的结果和真值句式和顺序的差别很大，这是为什么呢，请给我一些帮助
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.