mirror of
https://github.com/p-e-w/heretic.git
synced 2026-10-02 00:41:26 -07:00
feat: modifier plugins + ARA (#446)
* 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>
This commit is contained in:
co-authored by
kabachuha
joninco
Ashar
parent
71e6d5eb38
commit
662e4ba27e
@@ -9,6 +9,11 @@ print_debug_information = true
|
||||
|
||||
batch_size = 2
|
||||
max_response_length = 10
|
||||
|
||||
modifiers = [
|
||||
{ plugin = "heretic.modifiers.abliteration.Abliteration" },
|
||||
]
|
||||
|
||||
n_trials = 2
|
||||
n_startup_trials = 1
|
||||
|
||||
@@ -18,15 +23,13 @@ trial_index = 0
|
||||
model_action = "save"
|
||||
save_directory = "model"
|
||||
|
||||
row_normalization = "none"
|
||||
|
||||
[good_prompts]
|
||||
[[response_prefix_test_prompts]]
|
||||
dataset = "mlabonne/harmless_alpaca"
|
||||
commit = "02c6a92cfcf11bb0c387334f8146d149d65b587f"
|
||||
split = "train[:5]"
|
||||
column = "text"
|
||||
|
||||
[bad_prompts]
|
||||
[[response_prefix_test_prompts]]
|
||||
dataset = "mlabonne/harmful_behaviors"
|
||||
commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
|
||||
split = "train[:5]"
|
||||
@@ -43,3 +46,18 @@ dataset = "mlabonne/harmful_behaviors"
|
||||
commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
|
||||
split = "test[:5]"
|
||||
column = "text"
|
||||
|
||||
[modifier.Abliteration]
|
||||
row_normalization = "none"
|
||||
|
||||
[modifier.Abliteration.good_prompts]
|
||||
dataset = "mlabonne/harmless_alpaca"
|
||||
commit = "02c6a92cfcf11bb0c387334f8146d149d65b587f"
|
||||
split = "train[:5]"
|
||||
column = "text"
|
||||
|
||||
[modifier.Abliteration.bad_prompts]
|
||||
dataset = "mlabonne/harmful_behaviors"
|
||||
commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
|
||||
split = "train[:5]"
|
||||
column = "text"
|
||||
|
||||
Reference in New Issue
Block a user