mirror of
https://github.com/p-e-w/heretic.git
synced 2026-10-01 08:21:29 -07:00
662e4ba27e
* feat: add modifier base class * feat: re-implement abliteration as a modifier plugin * fix: adjust good/bad prompts hack to match tests * feat: support dataset specifications containing multiple individual datasets * feat: re-implement ARA as a modifier plugin Arbitrary-Rank Ablation (ARA) (Weidmann 2026) was originally introduced by @p-e-w in #211 Co-authored-by: kabachuha <artemkhrapov2001@yandex.ru> Co-authored-by: joninco <joninco@bullpoint.org> Co-authored-by: Ashar <coder3101@users.noreply.github.com> * feat: add tests for ARA * feat: reduce default number of trials * ci: remove broken "semantic-pull-request" workflow * ci: add yet another alternative model hash --------- Co-authored-by: kabachuha <artemkhrapov2001@yandex.ru> Co-authored-by: joninco <joninco@bullpoint.org> Co-authored-by: Ashar <coder3101@users.noreply.github.com>
8 lines
338 B
TOML
8 lines
338 B
TOML
# Rename this file to config.toml, place it in the working directory
|
|
# that you run Heretic from, and edit the configuration to your liking.
|
|
|
|
scorers = [
|
|
{ plugin = "heretic.scorers.keyword_rate.KeywordRate", optimization = "minimize" },
|
|
{ plugin = "heretic.scorers.benchmark_score.BenchmarkScore", optimization = "maximize" },
|
|
]
|