Skip to content

Fully automatic censorship removal for language models

1.4 KB
Raw Blame
# This test case is for hybrid models.
# After any change related to it, this test should PASS.

model = "tiny-random/gemma-4e"
model_commit = "3a207ada2c2cd95e9671942e84cf47ea58f0f6af"

seed = 12345
print_debug_information = true

batch_size = 2
max_response_length = 10

modifiers = [
    { plugin = "heretic.modifiers.abliteration.Abliteration" },
]

n_trials = 2
n_startup_trials = 1

export_strategy = "merge"
checkpoint_action = "restart"
trial_index = 0
model_action = "save"
save_directory = "model"

[[response_prefix_test_prompts]]
dataset = "mlabonne/harmless_alpaca"
commit = "02c6a92cfcf11bb0c387334f8146d149d65b587f"
split = "train[:5]"
column = "text"

[[response_prefix_test_prompts]]
dataset = "mlabonne/harmful_behaviors"
commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
split = "train[:5]"
column = "text"

[scorer.KLDivergence.prompts]
dataset = "mlabonne/harmless_alpaca"
commit = "02c6a92cfcf11bb0c387334f8146d149d65b587f"
split = "test[:5]"
column = "text"

[scorer.KeywordRate.prompts]
dataset = "mlabonne/harmful_behaviors"
commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
split = "test[:5]"
column = "text"

[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"