需要支持提取错误case，包括问题、标准答案、错误答案。 然后需要支持单测错误case，把错误case作为数据集，只载入问题、标准答案，然后让debug后的bmodel回答，测试debug效果。
-
Notifications
You must be signed in to change notification settings - Fork 0
fangz-ai/Model_EvaL
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
evaluator for self-attention LLMs on TPU of Sophgo
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published