Spaces:

Misbahuddin
/

amana

Sleeping

App Files Files Community

amana / eval

26.6 kB

Ctrl+K

Ctrl+K

3 contributors

History: 3 commits

Misbahuddin's picture

Phase 4.1: gate hardening — corroborate hard citations + enforce ELIG-4

438e8e8 about 1 month ago

build_testset.py

2.49 kB
Phase 4: eval harness + CI (deterministic safety gate + LLM-judge) about 1 month ago
run_eval.py

20.8 kB
Phase 4.1: gate hardening — corroborate hard citations + enforce ELIG-4 about 1 month ago
testset.json

3.28 kB
Phase 4: eval harness + CI (deterministic safety gate + LLM-judge) about 1 month ago