mlcommons / mlcommons/modelbench
calibrate French for new reference model selection
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 134
- Forks
- 36
- Avg merge
- 1d 11h
- Merged PRs (30d)
- 17
Description
Kurt says: "Ok. We have official approval to move forward at best speed with official FR benchmarks. We will replace Llama with phi 3.5 mini as the other reference SUT, and we will only benchmark SUTs that we did in english."
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
Start by locating the French benchmark configuration and the reference SUT selection in the repository. Check how the current Llama reference and English-only SUT coverage are represented, then verify that French benchmarks use phi 3.5 mini and only include SUTs benchmarked in English.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- internationalization, machine-learning, testing-qa
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100