Chatglm3 的ceval评估结果很差！ #582
Closed
githubjqh
started this conversation in
Show and tell
Replies: 1 comment
-
|
想问一下最后是怎么解决的呢？ |
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.
-
用ceval数据集和代码测试从modelscope下载的chatglm3-6b-base模型，最后精度结果平均值为30.65%。与https://cevalbenchmark.com/static/model.html?method=ChatGLM3-6B-base中给出的结果相差太远。谁知道什么原因吗？
Beta Was this translation helpful? Give feedback.
All reactions