Spaces:
Running
Running
Commit History
-
docs: add mathematical formulas, quality retention algorithm, and individual prompt evaluation examples
9b3fae3 -
fix: populate live analytics dashboard with real WildChat 10k benchmark metrics
9dc2825 -
feat: integrate allenai/WildChat-4.8M as flagship real dataset & update 10k benchmark results
0dfefae -
feat: add HF real workload datasets (10k), streaming benchmark results, and BYOK budget tests
7191aa9
-
feat: integrate 9 academic routing policies as explicit selectable gateway strategies and add benchmarking harness
d8d6846
-
feat: implement server-side FrugalGPT cascade router, prompt adaptation, and offline Pareto sweeps
26d7b76
-
feat: implement learned router and reproducible benchmark harness
41910df