Production Benchmarks
Named by 3 kept items in this workspace.
Search every workspace for Production Benchmarks. It matches the name as written, so it can find other things that share it.
The items that name it 3
Evaluation set of challenging conversations representative of production data, used to measure safe completions
evaluation set with challenging examples from production data for safe completions
Evaluation set of challenging, production-representative conversations used to measure not_unsafe rates across disallowed content categories
All technologies in this workspace.