add a proposal of Smart Coding benchmark suite

[safe-b]

Smart Coding benchmark suite: built on KubeEdge-lanvs

What type of PR is this?
/kind test
/kind design

What this PR does / why we need it:
The PR is a proposal to enhance a dataset by annotating the core code of the classic Python project, and then add project problems and App projects, etc., to finally complete the creation of the dataset and conduct test evaluation.
Which issue(s) this PR fixes:
#98
Fixes #

[hsj576]

The PR should further elaborate on how to implement this feature in Ianvs.

[MooreZheng]

This proposal is related to #98 and there are two advices.

1. Putting ianvs integration at the final stage would be risky for this project. The integration shall be started asap. As mentioned in the routine meeting, a recommended implementation from @IcyFeather233 is in https://github.com/IcyFeather233/ianvs/tree/dev, one can follow this readme to try llm single task learning and open compass.
2. It is not clear how would it be related to the SIG AI project. An architecture with ianvs is needed. E.g., considering dataset, metric in TestEnv Manager. You might want to take a look at https://github.com/kubeedge/ianvs/pull/122/files for architecture example.

[kubeedge-bot]

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by:
To complete the pull request process, please assign moorezheng after the PR has been reviewed.
You can assign the PR to them by writing /assign @moorezheng in a comment when ready.

The full list of commands accepted by this bot can be found here.

Needs approval from an approver in each of these files:

• OWNERS

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

[safe-b]

The logic of the subject is basically consistent with Meng Zhuo's government affairs model.
The comment data set of the code model is basically the same as that of the government model. The difference lies in the content of the issue data set. One question may have multiple answers.
The next step is training and testing.