navi-1 / debug / eval /
@Eugene Sukhodolskiy Eugene Sukhodolskiy authored on 8 May
..
prompts Slim eval rubric to 3 levels with one reference per axis 1 month ago
__init__.py Add eval system Phase 1 — message feedback signal 2 months ago
__main__.py Add eval system Phase 2 — rubric, expert prompts, judge skeleton 2 months ago
api.py Add eval system Phase 4 — read endpoints and background runner 2 months ago
cli.py Add eval system Phase 3 — judge runner end to end 2 months ago
db.py Add eval system Phase 4 — read endpoints and background runner 2 months ago
index.html Add pagination, search, and sorting to admin sessions 1 month ago
judge.py Slim eval rubric to 3 levels with one reference per axis 1 month ago
runner.py Add eval system Phase 4 — read endpoints and background runner 2 months ago
schema.py Slim eval rubric to 3 levels with one reference per axis 1 month ago
schema.sql Add eval system Phase 1 — message feedback signal 2 months ago