mlcommons/modelbench Issues
Hacky first run for Tyler
UpdatedTesting a model from HuggingFace
Closed 3Daily Scheduled Test Failure
UpdatedDaily Scheduled Test Failure
UpdatedDaily Scheduled Test Failure
UpdatedDump of Mistral scores
Closedprune list of plugins
Updated 1Make it easy to run with a new SUT
Updated 3Put ModelBench on PyPi
UpdatedRequest-level parallelism
UpdatedMake it work with 3.11, 3.12
UpdatedFinal grade scale/text
Closedupgrade coffee to v0.2.6
ClosedAnonymize SUTs in report
Closedreference is multiple models
UpdatedUse llamaguard 2
Updated