opencompass
opencompass copied to clipboard
[Feature] Support datasets in OpenAI/evals
Describe the feature
OpenAI/evals contains many community-sourced tasks, with about 400-500 datasets covering various languages and fields. Compared to other open-source datasets, they have very few questions, but many tasks come from users' real needs and inspiration when using GPT4, and many datasets give people a bright feeling.
Is there a way to directly use their datasets through a certain mechanism?
Will you implement it?
- [ ] I would like to implement this feature and create a PR!
Great idea.
Describe the feature
OpenAI/evals contains many community-sourced tasks, with about 400-500 datasets covering various languages and fields. Compared to other open-source datasets, they have very few questions, but many tasks come from users' real needs and inspiration when using GPT4, and many datasets give people a bright feeling.
Is there a way to directly use their datasets through a certain mechanism?
Will you implement it?
- [ ] I would like to implement this feature and create a PR!
Hi, has any progress on this thread?