-
Notifications
You must be signed in to change notification settings - Fork 46
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
OSPP: Implementation of Domain-Specific Large Model Benchmarking Based on KubeEdge-Ianvs #144
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The "print" in the code should be replaced by "LOGGER.info" (from core.common.log import LOGGER ").
@hsj576 Thank you for your advice! Now they are all replaced. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Rebases are needed.
-
There is a file with conflicts like docs/proposals/scenarios/llm-benchmarks/llm-benchmarks.md that needs to take care of. e.g., using rebase https://liwt31.github.io/2019/12/25/merge_rebase/.
-
all commits need sign-off, which can also be solved by using rebase
Commit sha: 9b7f9c5, Author: IcyFeather, Committer: IcyFeather; The sign-off is missing.
Commit sha: ce9f470, Author: IcyFeather, Committer: IcyFeather; The sign-off is missing.
To add your Signed-off-by line to every commit in this branch:
Ensure you have a local copy of your branch by checking out the pull request locally via command line.
In your local branch, run: git rebase HEAD~11 --signoff
Force push your changes to overwrite the branch: git push --force-with-lease origin dev
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Rebases are needed.
- There is a file with conflicts like docs/proposals/scenarios/llm-benchmarks/llm-benchmarks.md that needs to take care of. e.g., using rebase https://liwt31.github.io/2019/12/25/merge_rebase/.
- all commits need sign-off, which can also be solved by using rebase
Commit sha: 9b7f9c5, Author: IcyFeather, Committer: IcyFeather; The sign-off is missing.
Commit sha: ce9f470, Author: IcyFeather, Committer: IcyFeather; The sign-off is missing.To add your Signed-off-by line to every commit in this branch:
Ensure you have a local copy of your branch by checking out the pull request locally via command line.
In your local branch, run: git rebase HEAD~11 --signoff
Force push your changes to overwrite the branch: git push --force-with-lease origin dev
Reminder: There are three CI issues that remain to be resolved, mainly for Pylint, see https://github.com/kubeedge/ianvs/actions/runs/11268242806
@MooreZheng The similar pylint issues are described in #152 To solve this, sedna and ianvs need to corporate. We discussed this problem in the last week zoom meeting, and it seems that it should be discussed more to find a final solution. |
/lgtm |
@hsj576 might also want to review this project |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks fine, but we need to refine the Chinese words as in English.
examples/government/singletask_learning_bench/objective/testenv/acc.py
Outdated
Show resolved
Hide resolved
examples/government/singletask_learning_bench/subjective/testenv/llm_judgement.py
Outdated
Show resolved
Hide resolved
@MooreZheng I have changed Chinese words to English |
Overall it looks fine. Any comment from @hsj576 before merging? |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Good. There is only one Chinese statement right now and we are very close to the final version.
Currently, this pull request contains 25 commits, which can make maintenance difficult, considering the number of contributors, pull requests, and their commits in KubeEdge Ianvs. In the final stage, @IcyFeather233 can squash the commits into one using rebase techniques.
|
||
def extract_comprehensive_score(input_str): | ||
# extract overall points | ||
match = re.search(r"'综合得分': (\d+)", input_str) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
In the re.search of llm_judgement.py, we need to replace Chinese characters with English.
Signed-off-by: IcyFeather <[email protected]> add opencompass and llm singletask learning bench Signed-off-by: IcyFeather <[email protected]> update llm single task learning bench readme Signed-off-by: IcyFeather <[email protected]> add government benchmark Signed-off-by: IcyFeather <[email protected]> update government benchmark Signed-off-by: IcyFeather <[email protected]> update llm government benchmark implementation Signed-off-by: IcyFeather <[email protected]> update llm government benchmark implementation Signed-off-by: IcyFeather <[email protected]> update government README Signed-off-by: IcyFeather <[email protected]> update llm benchmark format Signed-off-by: IcyFeather <[email protected]> update government benchmark Signed-off-by: IcyFeather <[email protected]> update government benchmark dataset Signed-off-by: IcyFeather <[email protected]> add llm-benchmarks proposal Signed-off-by: IcyFeather <[email protected]> update llm benchmark proposal Signed-off-by: IcyFeather <[email protected]> update llm benchmark proposal Signed-off-by: IcyFeather <[email protected]> update llm benchmark proposal Signed-off-by: IcyFeather <[email protected]> translate llm-benchmark proposal Signed-off-by: IcyFeather <[email protected]> update proposal, add opencompass tutorial Signed-off-by: IcyFeather <[email protected]> update government benchmark sedna package Signed-off-by: IcyFeather <[email protected]> update government benchmark Signed-off-by: IcyFeather <[email protected]> update llm benchmark format Signed-off-by: IcyFeather <[email protected]> update llm benchmark format Signed-off-by: IcyFeather <[email protected]> fix pylint check problem Signed-off-by: IcyFeather <[email protected]> fix pylint check problem Signed-off-by: IcyFeather <[email protected]> fix pylint check problem Signed-off-by: IcyFeather <[email protected]> trans Chinese comments to English Signed-off-by: IcyFeather <[email protected]> add government llm benchmark Signed-off-by: IcyFeather <[email protected]> update government llm benchmark Signed-off-by: IcyFeather <[email protected]>
@MooreZheng All commits merged into one, and all Chinese words changed to English |
/lgtm |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This branch has conflicts that must be resolved
Use the web editor or the to resolve conflicts.
Conflicting files
core/testenvmanager/dataset/dataset.py
@MooreZheng conflicts are resolved |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Conflicts still exists
This branch has conflicts that must be resolved
Use the web editor or the to resolve conflicts.
Conflicting files
core/testenvmanager/dataset/dataset.py
Now conflicts have been solved after merging #162 |
/lgtm |
/lgtm |
/approve |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
All concerns are fixed. Well done!
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: MooreZheng The full list of commands accepted by this bot can be found here. The pull request process is described here
Needs approval from an approver in each of these files:
Approvers can indicate their approval by writing |
This PR is the implementation of #95