Qwen3.5-27B全量SFT效果不佳
#10298
Replies: 1 comment
-
|
请问训练 Qwen3.5-27B 和 训练qwen3vl config.yaml 里面除了模型路径 还有啥需要设置不同的吗 |
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.
-
在Qwen3.5-27B上做图文的全量SFT表现效果和基座本身差异不大，但在Qwen3的全量SFT提升效果很明显，是要考虑训练方法的问题吗？
Beta Was this translation helpful? Give feedback.
All reactions