mlcommons / mlcommons/modelbench
User bug: missing secrets for private modellab files when running public benchmark
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 134
- Forks
- 36
- Avg merge
- 1d 11h
- Merged PRs (30d)
- 17
Description
Sachi reports an error when running the command poetry run modelbench benchmark -m 10 --plugin-dir plugins/localModel/ --sut local_sut
I was trying to run modelbench, I think there were some latest changes in the last couple of days. When I try to run a sample of the benchmark, I get this:
raise MissingSecretValues.combine(missing_secrets)
modelgauge.secret_values.MissingSecretValues: Missing the following secrets:
scope='modellab_files' key='token' instructions='Please ask MLCommons admin for permission.'
I hadn't seen this before, is this for the latest practice set?
i added a new plugin - to read a local model. and it works with the "poetry run modelgauge run-csv-items sample.csv --sut local_sut
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Reproduce the poetry run modelbench benchmark -m 10 --plugin-dir plugins/localModel/ --sut local_sut command and compare it with the working poetry run modelgauge run-csv-items sample.csv --sut local_sut command. Trace when the modellab_files token is requested and determine the intended behavior for a local model; completion should include a verified benchmark run or a documented, actionable cause.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, testing-qa
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100